Merge feat/dedup-migration: client dedup library + NocoDB migration script + admin queue

# Conflicts:
#	.gitignore
#	src/lib/db/migrations/meta/_journal.json

tests/integration/dedup/client-merge.test.ts

@@ -0,0 +1,183 @@
+/**
+ * Client merge service — end-to-end integration test.
+ *
+ * Spins up two real clients in a real port via the factory helpers,
+ * attaches a few satellites (interest, contact, address, note),
+ * merges them, and asserts everything survived in the right place
+ * with the merge log written.
+ */
+import { describe, expect, it } from 'vitest';
+import { eq } from 'drizzle-orm';
+
+import { db } from '@/lib/db';
+import { clients, clientContacts, clientNotes, clientMergeLog } from '@/lib/db/schema/clients';
+import { interests } from '@/lib/db/schema/interests';
+import { mergeClients } from '@/lib/services/client-merge.service';
+import { makeClient, makePort, makeBerth } from '../../helpers/factories';
+
+describe('mergeClients', () => {
+  it('moves interests and contacts from loser to winner; archives loser; writes merge log', async () => {
+    const port = await makePort();
+    const winner = await makeClient({
+      portId: port.id,
+      overrides: { fullName: 'Marcus Laurent' },
+    });
+    const loser = await makeClient({
+      portId: port.id,
+      overrides: { fullName: 'Marcus Laurent (dup)' },
+    });
+
+    // Attach contact + interest to loser
+    await db.insert(clientContacts).values({
+      clientId: loser.id,
+      channel: 'email',
+      value: 'marcus@example.com',
+      isPrimary: true,
+    });
+    await db.insert(clientNotes).values({
+      clientId: loser.id,
+      authorId: 'test-user',
+      content: 'Loser-side note',
+    });
+    const berth = await makeBerth({ portId: port.id });
+    await db.insert(interests).values({
+      portId: port.id,
+      clientId: loser.id,
+      berthId: berth.id,
+      pipelineStage: 'open',
+      leadCategory: 'general_interest',
+    });
+
+    // ── Merge ─────────────────────────────────────────────────────────────
+    const result = await mergeClients({
+      winnerId: winner.id,
+      loserId: loser.id,
+      mergedBy: 'test-user',
+    });
+
+    expect(result.movedRows.interests).toBe(1);
+    expect(result.movedRows.contacts).toBe(1);
+    expect(result.movedRows.notes).toBe(1);
+
+    // ── Loser should be archived with mergedIntoClientId set ──────────────
+    const [archivedLoser] = await db.select().from(clients).where(eq(clients.id, loser.id));
+    expect(archivedLoser?.archivedAt).not.toBeNull();
+    expect(archivedLoser?.mergedIntoClientId).toBe(winner.id);
+
+    // ── All loser-side rows now point at the winner ───────────────────────
+    const winnerInterests = await db
+      .select()
+      .from(interests)
+      .where(eq(interests.clientId, winner.id));
+    expect(winnerInterests).toHaveLength(1);
+
+    const winnerContacts = await db
+      .select()
+      .from(clientContacts)
+      .where(eq(clientContacts.clientId, winner.id));
+    expect(winnerContacts.find((c) => c.value === 'marcus@example.com')).toBeDefined();
+
+    const winnerNotes = await db
+      .select()
+      .from(clientNotes)
+      .where(eq(clientNotes.clientId, winner.id));
+    expect(winnerNotes.find((n) => n.content === 'Loser-side note')).toBeDefined();
+
+    // ── Merge log row exists with snapshot ────────────────────────────────
+    const [log] = await db
+      .select()
+      .from(clientMergeLog)
+      .where(eq(clientMergeLog.id, result.mergeLogId));
+    expect(log?.survivingClientId).toBe(winner.id);
+    expect(log?.mergedClientId).toBe(loser.id);
+    expect(log?.mergedBy).toBe('test-user');
+    expect(log?.mergeDetails).toBeDefined();
+  });
+
+  it('refuses to merge a client into itself', async () => {
+    const port = await makePort();
+    const c = await makeClient({ portId: port.id });
+    await expect(mergeClients({ winnerId: c.id, loserId: c.id, mergedBy: 'u' })).rejects.toThrow(
+      /itself/i,
+    );
+  });
+
+  it('refuses to merge across different ports', async () => {
+    const portA = await makePort();
+    const portB = await makePort();
+    const a = await makeClient({ portId: portA.id });
+    const b = await makeClient({ portId: portB.id });
+    await expect(mergeClients({ winnerId: a.id, loserId: b.id, mergedBy: 'u' })).rejects.toThrow(
+      /different ports/i,
+    );
+  });
+
+  it('refuses to merge a client that has already been merged', async () => {
+    const port = await makePort();
+    const winner = await makeClient({ portId: port.id });
+    const loser = await makeClient({ portId: port.id });
+    // First merge succeeds.
+    await mergeClients({ winnerId: winner.id, loserId: loser.id, mergedBy: 'u' });
+    // Second merge of the same loser should refuse.
+    const winner2 = await makeClient({ portId: port.id });
+    await expect(
+      mergeClients({ winnerId: winner2.id, loserId: loser.id, mergedBy: 'u' }),
+    ).rejects.toThrow(/already merged/i);
+  });
+
+  it('drops duplicate contact rows during reattach', async () => {
+    const port = await makePort();
+    const winner = await makeClient({ portId: port.id });
+    const loser = await makeClient({ portId: port.id });
+
+    // Both have the same email contact.
+    await db.insert(clientContacts).values({
+      clientId: winner.id,
+      channel: 'email',
+      value: 'same@example.com',
+      isPrimary: true,
+    });
+    await db.insert(clientContacts).values({
+      clientId: loser.id,
+      channel: 'email',
+      value: 'same@example.com',
+      isPrimary: true,
+    });
+
+    const result = await mergeClients({
+      winnerId: winner.id,
+      loserId: loser.id,
+      mergedBy: 'u',
+    });
+
+    expect(result.movedRows.contacts).toBe(0); // duplicate dropped
+    const winnerEmails = await db
+      .select()
+      .from(clientContacts)
+      .where(eq(clientContacts.clientId, winner.id));
+    // Winner kept exactly one copy of the shared email.
+    expect(winnerEmails.filter((c) => c.value === 'same@example.com')).toHaveLength(1);
+  });
+
+  it('applies fieldChoices to copy loser values onto the winner', async () => {
+    const port = await makePort();
+    const winner = await makeClient({
+      portId: port.id,
+      overrides: { fullName: 'Marcus L.' },
+    });
+    const loser = await makeClient({
+      portId: port.id,
+      overrides: { fullName: 'Marcus Laurent' },
+    });
+
+    await mergeClients({
+      winnerId: winner.id,
+      loserId: loser.id,
+      mergedBy: 'u',
+      fieldChoices: { fullName: 'loser' },
+    });
+
+    const [updatedWinner] = await db.select().from(clients).where(eq(clients.id, winner.id));
+    expect(updatedWinner?.fullName).toBe('Marcus Laurent');
+  });
+});

tests/integration/dedup/match-candidates-api.test.ts

@@ -0,0 +1,157 @@
+/**
+ * Match-candidates API — integration test.
+ *
+ * Exercises the GET /api/v1/clients/match-candidates handler against a
+ * real port + clients pool. Verifies the dedup library's at-create
+ * suggestion path returns the right candidates and confidence tiers
+ * for the "use existing client?" form interruption.
+ */
+import { describe, expect, it } from 'vitest';
+
+import { db } from '@/lib/db';
+import { clientContacts } from '@/lib/db/schema/clients';
+import { getMatchCandidatesHandler } from '@/app/api/v1/clients/match-candidates/handlers';
+import { makeMockCtx, makeMockRequest } from '../../helpers/route-tester';
+import { makeClient, makePort } from '../../helpers/factories';
+
+interface MatchData {
+  clientId: string;
+  fullName: string;
+  score: number;
+  confidence: 'high' | 'medium' | 'low';
+  reasons: string[];
+  interestCount: number;
+}
+
+async function callHandler(
+  ctx: ReturnType<typeof makeMockCtx>,
+  query: Record<string, string>,
+): Promise<MatchData[]> {
+  const url = new URL('http://localhost/api/v1/clients/match-candidates');
+  for (const [k, v] of Object.entries(query)) url.searchParams.set(k, v);
+  const req = makeMockRequest('GET', url.toString());
+  const res = await getMatchCandidatesHandler(req, ctx);
+  expect(res.status).toBe(200);
+  const body = await res.json();
+  return body.data as MatchData[];
+}
+
+describe('GET /api/v1/clients/match-candidates', () => {
+  it('returns empty when nothing actionable was provided', async () => {
+    const port = await makePort();
+    const ctx = makeMockCtx({ portId: port.id });
+    const data = await callHandler(ctx, {});
+    expect(data).toEqual([]);
+  });
+
+  it('finds an existing client by exact email match (high confidence)', async () => {
+    const port = await makePort();
+    const ctx = makeMockCtx({ portId: port.id });
+    const existing = await makeClient({
+      portId: port.id,
+      overrides: { fullName: 'Marcus Laurent' },
+    });
+    await db.insert(clientContacts).values({
+      clientId: existing.id,
+      channel: 'email',
+      value: 'marcus@example.com',
+      isPrimary: true,
+    });
+    await db.insert(clientContacts).values({
+      clientId: existing.id,
+      channel: 'phone',
+      value: '+15551234567',
+      valueE164: '+15551234567',
+      isPrimary: true,
+    });
+
+    const data = await callHandler(ctx, {
+      email: 'Marcus@example.com',
+      phone: '+15551234567',
+      name: 'Marcus Laurent',
+    });
+
+    expect(data).toHaveLength(1);
+    expect(data[0]!.clientId).toBe(existing.id);
+    expect(data[0]!.confidence).toBe('high');
+    expect(data[0]!.reasons).toEqual(expect.arrayContaining(['email match', 'phone match']));
+  });
+
+  it('does not surface unrelated clients in the same port', async () => {
+    const port = await makePort();
+    const ctx = makeMockCtx({ portId: port.id });
+    const target = await makeClient({
+      portId: port.id,
+      overrides: { fullName: 'Marcus Laurent' },
+    });
+    await db.insert(clientContacts).values({
+      clientId: target.id,
+      channel: 'email',
+      value: 'marcus@example.com',
+      isPrimary: true,
+    });
+    // An unrelated client.
+    const unrelated = await makeClient({
+      portId: port.id,
+      overrides: { fullName: 'Bob Smith' },
+    });
+    await db.insert(clientContacts).values({
+      clientId: unrelated.id,
+      channel: 'email',
+      value: 'bob@example.org',
+      isPrimary: true,
+    });
+
+    const data = await callHandler(ctx, { email: 'marcus@example.com' });
+    expect(data.map((d) => d.clientId)).toEqual([target.id]);
+  });
+
+  it('returns medium-confidence partial matches', async () => {
+    // Same name, different contact info — Pattern F territory.
+    const port = await makePort();
+    const ctx = makeMockCtx({ portId: port.id });
+    const existing = await makeClient({
+      portId: port.id,
+      overrides: { fullName: 'Etiennette Clamouze' },
+    });
+    await db.insert(clientContacts).values({
+      clientId: existing.id,
+      channel: 'email',
+      value: 'clamouze.etiennette@gmail.com',
+      isPrimary: true,
+    });
+
+    const data = await callHandler(ctx, {
+      // Different email + phone, same name.
+      email: 'etiennette@the-manoah.com',
+      name: 'Etiennette Clamouze',
+    });
+
+    // Either no match (low confidence filtered out) or a medium one —
+    // either is fine. Critically, NOT high.
+    if (data.length > 0) {
+      expect(data[0]!.confidence).not.toBe('high');
+    }
+  });
+
+  it('does not leak across ports', async () => {
+    const portA = await makePort();
+    const portB = await makePort();
+
+    const ctxA = makeMockCtx({ portId: portA.id });
+    const inB = await makeClient({
+      portId: portB.id,
+      overrides: { fullName: 'In Port B' },
+    });
+    await db.insert(clientContacts).values({
+      clientId: inB.id,
+      channel: 'email',
+      value: 'b@example.com',
+      isPrimary: true,
+    });
+
+    // Caller is in port A, asking for an email that lives in port B.
+    const data = await callHandler(ctxA, { email: 'b@example.com' });
+    expect(data).toEqual([]);
+  });
+});

tests/unit/dedup/find-matches.test.ts

@@ -0,0 +1,379 @@
+/**
+ * Match-finding library — unit tests.
+ *
+ * Each duplicate cluster from the legacy NocoDB Interests audit (see
+ * docs/superpowers/specs/2026-05-03-dedup-and-migration-design.md §1.2)
+ * is encoded as a fixture here. The expected scoring tier (high / medium
+ * / low) is the design contract — if the algorithm starts returning
+ * "high" for a Pattern F case (Etiennette / Bruno+Bruce) it has lost
+ * the false-positive guard and we'll know immediately.
+ */
+import { describe, expect, it } from 'vitest';
+
+import { findClientMatches, type MatchCandidate } from '@/lib/dedup/find-matches';
+
+// Sensible defaults for tests — match the design's recommended thresholds.
+const THRESHOLDS = {
+  highScore: 90,
+  mediumScore: 50,
+};
+
+function candidate(partial: Partial<MatchCandidate> & { id: string }): MatchCandidate {
+  return {
+    id: partial.id,
+    fullName: partial.fullName ?? null,
+    surnameToken: partial.surnameToken ?? null,
+    emails: partial.emails ?? [],
+    phonesE164: partial.phonesE164 ?? [],
+    countryIso: partial.countryIso ?? null,
+  };
+}
+
+describe('findClientMatches', () => {
+  describe('Pattern A — pure double-submit (high confidence)', () => {
+    it('flags identical email + phone as high', () => {
+      // From real data: Deepak Ramchandani #624/#625, identical fields.
+      const incoming = candidate({
+        id: 'b',
+        fullName: 'Deepak Ramchandani',
+        surnameToken: 'ramchandani',
+        emails: ['dannyrams8888@gmail.com'],
+        phonesE164: ['+17215868888'],
+      });
+      const pool = [
+        candidate({
+          id: 'a',
+          fullName: 'Deepak Ramchandani',
+          surnameToken: 'ramchandani',
+          emails: ['dannyrams8888@gmail.com'],
+          phonesE164: ['+17215868888'],
+        }),
+      ];
+
+      const matches = findClientMatches(incoming, pool, THRESHOLDS);
+
+      expect(matches).toHaveLength(1);
+      expect(matches[0]!.candidate.id).toBe('a');
+      expect(matches[0]!.score).toBeGreaterThanOrEqual(90);
+      expect(matches[0]!.confidence).toBe('high');
+      expect(matches[0]!.reasons).toEqual(expect.arrayContaining(['email match', 'phone match']));
+    });
+  });
+
+  describe('Pattern B — same email, different phone format (high)', () => {
+    it('high confidence when phones already normalize-equal', () => {
+      // From real data: Howard Wiarda #236/#536, "574-274-0548" vs "+15742740548".
+      // After normalization both phones are the same E.164, so the rule fires.
+      const incoming = candidate({
+        id: 'b',
+        fullName: 'Howard Wiarda',
+        surnameToken: 'wiarda',
+        emails: ['hwiarda@hotmail.com'],
+        phonesE164: ['+15742740548'],
+      });
+      const pool = [
+        candidate({
+          id: 'a',
+          fullName: 'Howard Wiarda',
+          surnameToken: 'wiarda',
+          emails: ['hwiarda@hotmail.com'],
+          phonesE164: ['+15742740548'],
+        }),
+      ];
+
+      const matches = findClientMatches(incoming, pool, THRESHOLDS);
+
+      expect(matches[0]!.confidence).toBe('high');
+      expect(matches[0]!.score).toBeGreaterThanOrEqual(90);
+    });
+  });
+
+  describe('Pattern C — name capitalization variant (high)', () => {
+    it('treats lowercase + uppercase as the same person when surname-token + email + phone all match', () => {
+      // From real data: Nicolas Ruiz #681/#682/#683, email differs only by case.
+      const incoming = candidate({
+        id: 'b',
+        fullName: 'Nicolas Ruiz',
+        surnameToken: 'ruiz',
+        emails: ['ruiz.nicolas@ufl.edu'],
+        phonesE164: ['+17862006617'],
+      });
+      const pool = [
+        candidate({
+          id: 'a',
+          fullName: 'Nicolas Ruiz',
+          surnameToken: 'ruiz',
+          emails: ['ruiz.nicolas@ufl.edu'],
+          phonesE164: ['+17862006617'],
+        }),
+      ];
+
+      const matches = findClientMatches(incoming, pool, THRESHOLDS);
+
+      expect(matches[0]!.confidence).toBe('high');
+    });
+  });
+
+  describe('Pattern D — name shortening (high)', () => {
+    it('Chris vs Christopher with same email + phone scores high', () => {
+      // From real data: Chris Allen #700 vs Christopher Allen #534.
+      const incoming = candidate({
+        id: 'b',
+        fullName: 'Chris Allen',
+        surnameToken: 'allen',
+        emails: ['chris@thundercatsports.com'],
+        phonesE164: ['+17814548950'],
+      });
+      const pool = [
+        candidate({
+          id: 'a',
+          fullName: 'Christopher Allen',
+          surnameToken: 'allen',
+          emails: ['chris@thundercatsports.com'],
+          phonesE164: ['+17814548950'],
+        }),
+      ];
+
+      const matches = findClientMatches(incoming, pool, THRESHOLDS);
+
+      expect(matches[0]!.confidence).toBe('high');
+    });
+  });
+
+  describe('Pattern E — typo on resubmit', () => {
+    it('same email + nearly-identical phone (typo in last digits) scores high', () => {
+      // Christopher Camazou #649/#650 — phone differs in last 4 digits but
+      // everything else matches. Exact phone equality fails; email exact
+      // match alone (60) + name-token match (20) puts us in medium tier.
+      // The user can confirm the merge.
+      const incoming = candidate({
+        id: 'b',
+        fullName: 'Christopher Camazou',
+        surnameToken: 'camazou',
+        emails: ['camazou11@gmail.com'],
+        phonesE164: ['+33608334455'],
+      });
+      const pool = [
+        candidate({
+          id: 'a',
+          fullName: 'Christopher Camazou',
+          surnameToken: 'camazou',
+          emails: ['camazou11@gmail.com'],
+          phonesE164: ['+33608336549'],
+        }),
+      ];
+
+      const matches = findClientMatches(incoming, pool, THRESHOLDS);
+
+      expect(matches).toHaveLength(1);
+      // Email + name match without phone match — strong but not certain.
+      expect(matches[0]!.confidence).toMatch(/^(high|medium)$/);
+      expect(matches[0]!.score).toBeGreaterThanOrEqual(70);
+    });
+
+    it('Constanzo / Costanzo surname typo with same email + phone scores high', () => {
+      // Gianfranco Di Constanzo #585 vs Di Costanzo #336 — same email + phone
+      // and only a 1-letter surname typo. This is a strong "same client,
+      // multiple yachts" signal — the design's signature win.
+      const incoming = candidate({
+        id: 'b',
+        fullName: 'Gianfranco Di Constanzo',
+        surnameToken: 'constanzo',
+        emails: ['gdc@nauticall.com'],
+        phonesE164: ['+17542628669'],
+      });
+      const pool = [
+        candidate({
+          id: 'a',
+          fullName: 'Gianfranco Di Costanzo',
+          surnameToken: 'costanzo',
+          emails: ['gdc@nauticall.com'],
+          phonesE164: ['+17542628669'],
+        }),
+      ];
+
+      const matches = findClientMatches(incoming, pool, THRESHOLDS);
+
+      expect(matches[0]!.confidence).toBe('high');
+      expect(matches[0]!.score).toBeGreaterThanOrEqual(90);
+    });
+  });
+
+  describe('Pattern F — hard cases (must NOT auto-merge)', () => {
+    it('same name with different country phone + different email scores at most medium', () => {
+      // Etiennette Clamouze #188/#717 — same name but completely different
+      // email + phone (and the phones are in different country codes,
+      // suggesting either a relative, a coworker, or a name-collision).
+      // We must NOT classify this as "high" or it would force-merge two
+      // distinct people.
+      const incoming = candidate({
+        id: 'b',
+        fullName: 'Etiennette Clamouze',
+        surnameToken: 'clamouze',
+        emails: ['etiennette@the-manoah.com'],
+        phonesE164: ['+12645815607'],
+        countryIso: 'AI',
+      });
+      const pool = [
+        candidate({
+          id: 'a',
+          fullName: 'Etiennette Clamouze',
+          surnameToken: 'clamouze',
+          emails: ['clamouze.etiennette@gmail.com'],
+          phonesE164: ['+33767780640'],
+          countryIso: 'FR',
+        }),
+      ];
+
+      const matches = findClientMatches(incoming, pool, THRESHOLDS);
+
+      // Surname-token + name-exact match should score in medium tier so
+      // the pair lands in the review queue but doesn't auto-merge.
+      if (matches.length > 0) {
+        expect(matches[0]!.confidence).not.toBe('high');
+        expect(matches[0]!.score).toBeLessThan(90);
+      }
+    });
+
+    it('shared email between two clearly different names is medium not high', () => {
+      // Bruno Joyerot #18 vs Bruce Hearn #19 — Bruno's row shows email
+      // belonging to "catherine elaine hearn" (Bruce's spouse). Same
+      // household phone area code. Name overlap is partial. Don't merge.
+      const incoming = candidate({
+        id: 'b',
+        fullName: 'Bruce Hearn',
+        surnameToken: 'hearn',
+        emails: ['bhearn1063@gmail.com'],
+        phonesE164: ['+12642358840'],
+      });
+      const pool = [
+        candidate({
+          id: 'a',
+          fullName: 'Bruno Joyerot',
+          surnameToken: 'joyerot',
+          emails: ['catherineelainehearn@gmail.com'],
+          phonesE164: ['+12642352816'],
+        }),
+      ];
+
+      const matches = findClientMatches(incoming, pool, THRESHOLDS);
+
+      // Names don't match, emails don't match, phones differ — there's
+      // no reason for this to surface at all. Either no match or low.
+      if (matches.length > 0) {
+        expect(matches[0]!.confidence).toBe('low');
+      }
+    });
+  });
+
+  describe('Negative evidence — same email but different country phone', () => {
+    it('reduces score when email matches but phone country differs', () => {
+      // Constructed: same email, but one phone is +33 (FR) and the other
+      // is +1 (US). Likely a shared-inbox spouse situation. We want
+      // medium tier so it lands in review, not high tier.
+      const incoming = candidate({
+        id: 'b',
+        fullName: 'Test User',
+        surnameToken: 'user',
+        emails: ['shared@example.com'],
+        phonesE164: ['+15551234567'],
+        countryIso: 'US',
+      });
+      const pool = [
+        candidate({
+          id: 'a',
+          fullName: 'Test User',
+          surnameToken: 'user',
+          emails: ['shared@example.com'],
+          phonesE164: ['+33611111111'],
+          countryIso: 'FR',
+        }),
+      ];
+
+      const matches = findClientMatches(incoming, pool, THRESHOLDS);
+
+      // Email match alone would be 60 + name token match 20 = 80 (medium).
+      // Negative evidence (different phone country) brings it down further.
+      expect(matches[0]!.confidence).toBe('medium');
+    });
+  });
+
+  describe('Blocking — only relevant candidates are scored', () => {
+    it('does not score candidates with no shared emails / phones / surname token', () => {
+      const incoming = candidate({
+        id: 'newbie',
+        fullName: 'Alice Smith',
+        surnameToken: 'smith',
+        emails: ['alice@example.com'],
+        phonesE164: ['+15551234567'],
+      });
+      const pool = [
+        candidate({
+          id: 'unrelated1',
+          fullName: 'Bob Jones',
+          surnameToken: 'jones',
+          emails: ['bob@example.org'],
+          phonesE164: ['+33611111111'],
+        }),
+        candidate({
+          id: 'unrelated2',
+          fullName: 'Carol White',
+          surnameToken: 'white',
+          emails: ['carol@example.net'],
+          phonesE164: ['+447700900111'],
+        }),
+      ];
+
+      const matches = findClientMatches(incoming, pool, THRESHOLDS);
+
+      expect(matches).toHaveLength(0);
+    });
+  });
+
+  describe('Empty pool', () => {
+    it('returns no matches when the pool is empty', () => {
+      const incoming = candidate({
+        id: 'a',
+        fullName: 'Alice',
+        emails: ['alice@example.com'],
+      });
+      expect(findClientMatches(incoming, [], THRESHOLDS)).toEqual([]);
+    });
+  });
+
+  describe('Sort order', () => {
+    it('returns matches sorted by score descending', () => {
+      const incoming = candidate({
+        id: 'incoming',
+        fullName: 'John Smith',
+        surnameToken: 'smith',
+        emails: ['john@example.com'],
+        phonesE164: ['+15551234567'],
+      });
+      const pool = [
+        candidate({
+          // High match — same email + phone
+          id: 'high-match',
+          fullName: 'John Smith',
+          surnameToken: 'smith',
+          emails: ['john@example.com'],
+          phonesE164: ['+15551234567'],
+        }),
+        candidate({
+          // Medium match — same email only
+          id: 'medium-match',
+          fullName: 'Different Person',
+          surnameToken: 'person',
+          emails: ['john@example.com'],
+          phonesE164: ['+33611111111'],
+        }),
+      ];
+
+      const matches = findClientMatches(incoming, pool, THRESHOLDS);
+
+      expect(matches.length).toBeGreaterThanOrEqual(2);
+      expect(matches[0]!.candidate.id).toBe('high-match');
+      expect(matches[0]!.score).toBeGreaterThan(matches[1]!.score);
+    });
+  });
+});

tests/unit/dedup/migration-transform.test.ts

@@ -0,0 +1,213 @@
+/**
+ * Migration transform — fixture-based regression test.
+ *
+ * Feeds the transform a small frozen NocoDB snapshot containing one
+ * representative row from each duplicate pattern documented in
+ * docs/superpowers/specs/2026-05-03-dedup-and-migration-design.md §1.2,
+ * and asserts the resulting plan matches the algorithm's expected
+ * behavior. If any future change starts merging Pattern F (Etiennette
+ * Clamouze) or stops merging Pattern A (Deepak Ramchandani), this
+ * test fails immediately.
+ */
+import { describe, expect, it } from 'vitest';
+
+import { transformSnapshot } from '@/lib/dedup/migration-transform';
+import type { NocoDbRow, NocoDbSnapshot } from '@/lib/dedup/nocodb-source';
+
+function row(fields: Partial<NocoDbRow> & { Id: number }): NocoDbRow {
+  return fields as NocoDbRow;
+}
+
+const FIXTURE: NocoDbSnapshot = {
+  fetchedAt: '2026-05-03T12:00:00.000Z',
+  berths: [],
+  residentialInterests: [],
+  websiteInterestSubmissions: [],
+  websiteContactFormSubmissions: [],
+  websiteBerthEoiSupplements: [],
+  interests: [
+    // Pattern A: pure double-submit (Deepak Ramchandani #624/#625)
+    row({
+      Id: 624,
+      'Full Name': 'Deepak Ramchandani',
+      'Email Address': 'dannyrams8888@gmail.com',
+      'Phone Number': '+17215868888',
+      'Sales Process Level': 'General Qualified Interest',
+    }),
+    row({
+      Id: 625,
+      'Full Name': 'Deepak Ramchandani',
+      'Email Address': 'dannyrams8888@gmail.com',
+      'Phone Number': '+17215868888',
+      'Sales Process Level': 'General Qualified Interest',
+    }),
+
+    // Pattern B: phone format variance (Howard Wiarda #236/#536)
+    row({
+      Id: 236,
+      'Full Name': 'Howard Wiarda',
+      'Email Address': 'hwiarda@hotmail.com',
+      'Phone Number': '574-274-0548',
+      'Place of Residence': 'USA',
+      'Sales Process Level': 'General Qualified Interest',
+    }),
+    row({
+      Id: 536,
+      'Full Name': 'Howard Wiarda',
+      'Email Address': 'hwiarda@hotmail.com',
+      'Phone Number': '+15742740548',
+      'Sales Process Level': 'General Qualified Interest',
+    }),
+
+    // Pattern C: name capitalization (Nicolas Ruiz #681/#682/#683 — three rows)
+    row({
+      Id: 681,
+      'Full Name': 'Nicolas Ruiz',
+      'Email Address': 'ruiz.nicolas@ufl.edu',
+      'Phone Number': '+17862006617',
+      'Sales Process Level': 'General Qualified Interest',
+    }),
+    row({
+      Id: 682,
+      'Full Name': 'Nicolas Ruiz',
+      'Email Address': 'ruiz.nicolas@ufl.edu',
+      'Phone Number': '+17862006617',
+      'Sales Process Level': 'Specific Qualified Interest',
+    }),
+    row({
+      Id: 683,
+      'Full Name': 'Nicolas Ruiz',
+      'Email Address': 'Ruiz.Nicolas@ufl.edu',
+      'Phone Number': '+17862006617',
+      'Sales Process Level': 'General Qualified Interest',
+    }),
+
+    // Pattern E: surname typo with same email + phone (Constanzo/Costanzo)
+    row({
+      Id: 336,
+      'Full Name': 'Gianfranco Di Costanzo',
+      'Email Address': 'gdc@nauticall.com',
+      'Phone Number': '+17542628669',
+      'Yacht Name': 'GEMINI',
+      'Sales Process Level': 'Contract Signed',
+    }),
+    row({
+      Id: 585,
+      'Full Name': 'Gianfranco Di Constanzo',
+      'Email Address': 'gdc@nauticall.com',
+      'Phone Number': '+17542628669',
+      'Yacht Name': 'CALYPSO',
+      'Sales Process Level': 'Signed EOI and NDA',
+    }),
+
+    // Pattern F: same name, different country phones (Etiennette Clamouze)
+    row({
+      Id: 188,
+      'Full Name': 'Etiennette Clamouze',
+      'Email Address': 'clamouze.etiennette@gmail.com',
+      'Phone Number': '+33767780640',
+      'Sales Process Level': 'General Qualified Interest',
+    }),
+    row({
+      Id: 717,
+      'Full Name': 'Etiennette Clamouze',
+      'Email Address': 'Etiennette@the-manoah.com',
+      'Phone Number': '+12645815607',
+      'Sales Process Level': 'General Qualified Interest',
+    }),
+
+    // Single isolated row to verify non-duplicates pass through
+    row({
+      Id: 999,
+      'Full Name': 'Lone Wolf',
+      'Email Address': 'lone@example.com',
+      'Phone Number': '+15551234567',
+      'Sales Process Level': 'General Qualified Interest',
+    }),
+  ],
+};
+
+describe('transformSnapshot — fixture regression', () => {
+  it('produces the expected number of clients + interests', () => {
+    const plan = transformSnapshot(FIXTURE);
+
+    // 12 input rows → 7 unique clients (Deepak: 1, Wiarda: 1, Ruiz: 1,
+    // Constanzo: 1, Etiennette x2: 2, Lone: 1). Etiennette stays as 2
+    // because Pattern F is correctly NOT auto-merged.
+    expect(plan.stats.outputClients).toBe(7);
+    expect(plan.stats.outputInterests).toBe(12); // one per source row
+  });
+
+  it('auto-links every Pattern A–E cluster', () => {
+    const plan = transformSnapshot(FIXTURE);
+    const linkedSourceIds = new Set<number>();
+    for (const link of plan.autoLinks) {
+      linkedSourceIds.add(link.leadSourceId);
+      for (const merged of link.mergedSourceIds) {
+        linkedSourceIds.add(merged);
+      }
+    }
+
+    // Pattern A: 624 + 625
+    expect(linkedSourceIds.has(624) && linkedSourceIds.has(625)).toBe(true);
+    // Pattern B: 236 + 536
+    expect(linkedSourceIds.has(236) && linkedSourceIds.has(536)).toBe(true);
+    // Pattern C: 681 + 682 + 683 (three-way)
+    expect(linkedSourceIds.has(681) && linkedSourceIds.has(682) && linkedSourceIds.has(683)).toBe(
+      true,
+    );
+    // Pattern E: 336 + 585
+    expect(linkedSourceIds.has(336) && linkedSourceIds.has(585)).toBe(true);
+  });
+
+  it('does NOT auto-link Pattern F (Etiennette Clamouze, different country)', () => {
+    const plan = transformSnapshot(FIXTURE);
+    const linkedSourceIds = new Set<number>();
+    for (const link of plan.autoLinks) {
+      linkedSourceIds.add(link.leadSourceId);
+      for (const merged of link.mergedSourceIds) {
+        linkedSourceIds.add(merged);
+      }
+    }
+    // Both Etiennette rows must remain as separate clients.
+    expect(linkedSourceIds.has(188)).toBe(false);
+    expect(linkedSourceIds.has(717)).toBe(false);
+  });
+
+  it('preserves every interest as its own row even when clients merge', () => {
+    const plan = transformSnapshot(FIXTURE);
+    const sourceIds = plan.interests.map((i) => i.sourceId).sort((a, b) => a - b);
+    expect(sourceIds).toEqual([188, 236, 336, 536, 585, 624, 625, 681, 682, 683, 717, 999]);
+  });
+
+  it('maps the legacy 8-stage enum to new pipeline stages', () => {
+    const plan = transformSnapshot(FIXTURE);
+    const stagesById = new Map(plan.interests.map((i) => [i.sourceId, i.pipelineStage]));
+    expect(stagesById.get(681)).toBe('open'); // General Qualified Interest
+    expect(stagesById.get(682)).toBe('details_sent'); // Specific Qualified Interest
+    expect(stagesById.get(336)).toBe('contract_signed'); // Contract Signed
+    expect(stagesById.get(585)).toBe('eoi_signed'); // Signed EOI and NDA
+  });
+
+  it('attaches different yachts to one merged Constanzo client', () => {
+    const plan = transformSnapshot(FIXTURE);
+    const constanzoClient = plan.clients.find(
+      (c) => c.sourceIds.includes(336) && c.sourceIds.includes(585),
+    );
+    expect(constanzoClient).toBeDefined();
+    const yachtsForConstanzo = plan.interests
+      .filter((i) => i.clientTempId === constanzoClient!.tempId)
+      .map((i) => i.yachtName)
+      .sort();
+    expect(yachtsForConstanzo).toEqual(['CALYPSO', 'GEMINI']);
+  });
+
+  it('produces deterministic output (same input → same plan)', () => {
+    // The transform is pure — running it twice should yield bit-identical
+    // results. Catches order-dependent bugs in the dedup clustering.
+    const a = transformSnapshot(FIXTURE);
+    const b = transformSnapshot(FIXTURE);
+    expect(JSON.stringify(a.stats)).toBe(JSON.stringify(b.stats));
+    expect(a.autoLinks.length).toBe(b.autoLinks.length);
+  });
+});

tests/unit/dedup/normalize.test.ts

@@ -0,0 +1,270 @@
+/**
+ * Normalization library — unit tests.
+ *
+ * Every fixture here comes from real dirty values observed in the legacy
+ * NocoDB Interests table during the 2026-05-03 audit (see
+ * docs/superpowers/specs/2026-05-03-dedup-and-migration-design.md §1.3).
+ * The point is regression-prevention: if any of these patterns ever
+ * stops normalizing the way it should, dedup quality silently drops.
+ */
+import { describe, expect, it } from 'vitest';
+
+import {
+  normalizeName,
+  normalizeEmail,
+  normalizePhone,
+  resolveCountry,
+} from '@/lib/dedup/normalize';
+
+describe('normalizeName', () => {
+  it('returns null fields for empty / null input', () => {
+    expect(normalizeName('')).toEqual({ display: '', normalized: '', surnameToken: undefined });
+    expect(normalizeName('   ')).toEqual({
+      display: '',
+      normalized: '',
+      surnameToken: undefined,
+    });
+  });
+
+  it('trims leading/trailing whitespace', () => {
+    expect(normalizeName('  Marcus Laurent  ')).toMatchObject({
+      display: 'Marcus Laurent',
+      normalized: 'marcus laurent',
+    });
+  });
+
+  it('collapses repeated internal whitespace to a single space', () => {
+    // From real data: "Arthur  Matthews" (#183), "Corinne  Roche" (#208).
+    expect(normalizeName('Arthur  Matthews').display).toBe('Arthur Matthews');
+    expect(normalizeName('Corinne   Roche').display).toBe('Corinne Roche');
+  });
+
+  it('replaces embedded carriage returns and newlines with single spaces', () => {
+    // From real data: "Andrei \nVAGNANOV" (#178), "Daniel\r PRZEDBORSKI" (#175).
+    expect(normalizeName('Andrei \nVAGNANOV').display).toBe('Andrei Vagnanov');
+    expect(normalizeName('Daniel\r PRZEDBORSKI').display).toBe('Daniel Przedborski');
+  });
+
+  it('title-cases ALL-CAPS surnames while keeping given name title-cased', () => {
+    // From real data: "Jona ANDERSEN" (#232), "Duane SALTSGAVER" (#227),
+    // "Marcos DALLA PRIA" (#165).
+    expect(normalizeName('Jona ANDERSEN').display).toBe('Jona Andersen');
+    expect(normalizeName('Duane SALTSGAVER').display).toBe('Duane Saltsgaver');
+    // Particle 'dalla' stays lowercase mid-name.
+    expect(normalizeName('Marcos DALLA PRIA').display).toBe('Marcos dalla Pria');
+  });
+
+  it('title-cases lowercased entries', () => {
+    // From real data: "antony amaral" (#665), "david rosenbloom" (#239),
+    // "john Tickner" (#247).
+    expect(normalizeName('antony amaral').display).toBe('Antony Amaral');
+    expect(normalizeName('david rosenbloom').display).toBe('David Rosenbloom');
+    expect(normalizeName('john Tickner').display).toBe('John Tickner');
+  });
+
+  it('keeps Romance and Germanic particles lowercase mid-name', () => {
+    // From real data: "Olav van Velsen" (#526), "Bruno Joyerot" (#18),
+    // "OLIVIER DAIN" (#677). Also synthetic "Carla de la Cruz".
+    expect(normalizeName('Olav van Velsen').display).toBe('Olav van Velsen');
+    expect(normalizeName('Carla de la Cruz').display).toBe('Carla de la Cruz');
+    expect(normalizeName('OLIVIER DAIN').display).toBe('Olivier Dain');
+  });
+
+  it('preserves O‘-prefixed Irish surnames as title-case', () => {
+    expect(normalizeName("liam o'brien").display).toBe("Liam O'Brien");
+  });
+
+  it('keeps the slash-with-company structure intact', () => {
+    // From real data: "Daniel Wainstein / 7 Knots, LLC" (#637),
+    // "Bruno Joyerot / SAS TIKI" (#18).
+    expect(normalizeName('Daniel Wainstein / 7 Knots, LLC').display).toBe(
+      'Daniel Wainstein / 7 Knots, LLC',
+    );
+    expect(normalizeName('Bruno Joyerot / SAS TIKI').display).toBe('Bruno Joyerot / SAS TIKI');
+  });
+
+  it('exposes the last non-particle token as surnameToken (lowercase) for blocking', () => {
+    expect(normalizeName('Marcus Laurent').surnameToken).toBe('laurent');
+    expect(normalizeName('Olav van Velsen').surnameToken).toBe('velsen');
+    expect(normalizeName('Carla de la Cruz').surnameToken).toBe('cruz');
+    expect(normalizeName("Liam O'Brien").surnameToken).toBe("o'brien");
+  });
+
+  it('handles single-token names — surnameToken is the only token', () => {
+    expect(normalizeName('Madonna').surnameToken).toBe('madonna');
+  });
+
+  it('produces a normalized form that is always lowercase', () => {
+    expect(normalizeName('Andrei VAGNANOV').normalized).toBe('andrei vagnanov');
+    expect(normalizeName('Daniel Wainstein / 7 Knots, LLC').normalized).toBe(
+      'daniel wainstein / 7 knots, llc',
+    );
+  });
+});
+
+describe('normalizeEmail', () => {
+  it('returns null for empty / null inputs', () => {
+    expect(normalizeEmail('')).toBeNull();
+    expect(normalizeEmail('   ')).toBeNull();
+  });
+
+  it('lowercases and trims', () => {
+    // From real data: "Arthur@laser-align.com" vs "arthur@laser-align.com" (#183/#686).
+    expect(normalizeEmail('Arthur@laser-align.com')).toBe('arthur@laser-align.com');
+    expect(normalizeEmail('  marcus@example.com  ')).toBe('marcus@example.com');
+  });
+
+  it('lowercases capitalized localparts', () => {
+    // From real data: "Bmalone850@gmail.com" (#489), "Hef355@yahoo.com" (#533),
+    // "Donclaytonmusic@gmail.com" (#679).
+    expect(normalizeEmail('Bmalone850@gmail.com')).toBe('bmalone850@gmail.com');
+    expect(normalizeEmail('Hef355@yahoo.com')).toBe('hef355@yahoo.com');
+  });
+
+  it('preserves plus-aliases — both legitimate and tricks', () => {
+    // Per design §3.2: "+aliases" are not stripped. Compare by full localpart.
+    expect(normalizeEmail('marcus+sales@example.com')).toBe('marcus+sales@example.com');
+  });
+
+  it('returns null for invalid email shapes', () => {
+    expect(normalizeEmail('not-an-email')).toBeNull();
+    expect(normalizeEmail('@example.com')).toBeNull();
+    expect(normalizeEmail('user@')).toBeNull();
+    expect(normalizeEmail('user@.com')).toBeNull();
+  });
+});
+
+describe('normalizePhone', () => {
+  it('returns null for empty / whitespace / null', () => {
+    expect(normalizePhone('', 'AI')).toBeNull();
+    expect(normalizePhone('   ', 'AI')).toBeNull();
+  });
+
+  it('parses a plain E.164 number', () => {
+    expect(normalizePhone('+15742740548', 'US')).toMatchObject({
+      e164: '+15742740548',
+      country: 'US',
+    });
+  });
+
+  it('strips embedded carriage returns and trailing whitespace', () => {
+    // From real data: "+1-264-235-8840\r" (#19), "+1-264-772-3272\r" (#20).
+    const out = normalizePhone('+1-264-235-8840\r', 'AI');
+    expect(out?.e164).toBe('+12642358840');
+  });
+
+  it('strips dashes, dots, parens, single quotes, spaces in a single pass', () => {
+    // From real data: "'+1.214.603.4235" (#205), "574-274-0548" (#236),
+    // "+1-264-235-8840" (#19), "+1 (212) 555-0123" (synthetic).
+    expect(normalizePhone("'+1.214.603.4235", 'US')?.e164).toBe('+12146034235');
+    expect(normalizePhone('574-274-0548', 'US')?.e164).toBe('+15742740548');
+    expect(normalizePhone('+1 (212) 555-0123', 'US')?.e164).toBe('+12125550123');
+  });
+
+  it('converts a leading 00 prefix to + (international dialling)', () => {
+    // From real data: "00447956657022" (#216), "0033651381036" (#702).
+    expect(normalizePhone('00447956657022', 'GB')?.e164).toBe('+447956657022');
+    expect(normalizePhone('0033651381036', 'FR')?.e164).toBe('+33651381036');
+  });
+
+  it('uses defaultCountry when input has no international prefix', () => {
+    // From real data: "0690699699" (#203, French local), "0651381036" (#701).
+    expect(normalizePhone('0690699699', 'FR')?.e164).toBe('+33690699699');
+    expect(normalizePhone('0651381036', 'FR')?.e164).toBe('+33651381036');
+  });
+
+  it('returns null when there is no prefix AND no defaultCountry', () => {
+    // The migration script flags these for human review.
+    const out = normalizePhone('5742740548');
+    expect(out?.e164 ?? null).toBeNull();
+  });
+
+  it('flags placeholder all-zeros numbers and returns null', () => {
+    // From real data: "+447000000000" (#641, "Milos Vitkovic" — clearly fake).
+    const out = normalizePhone('+447000000000', 'GB');
+    expect(out?.flagged).toBe('placeholder');
+    expect(out?.e164).toBeNull();
+  });
+
+  it('flags multi-number fields and uses the first segment', () => {
+    // From real data: "0677580750/0690511494" (#209). Other separators: ; ,
+    const slash = normalizePhone('0677580750/0690511494', 'FR');
+    expect(slash?.flagged).toBe('multi_number');
+    expect(slash?.e164).toBe('+33677580750');
+
+    const semi = normalizePhone('+33611111111;+33622222222', 'FR');
+    expect(semi?.flagged).toBe('multi_number');
+    expect(semi?.e164).toBe('+33611111111');
+  });
+
+  it('flags genuinely unparseable input as `unparseable`', () => {
+    const out = normalizePhone('xyz-not-a-phone', 'US');
+    expect(out?.flagged).toBe('unparseable');
+    expect(out?.e164).toBeNull();
+  });
+
+  it('strips an apostrophe-prefix without breaking the parse', () => {
+    // From real data: leading "'" copy-pasted from spreadsheets escapes
+    // numeric-cell coercion. Should be invisible to dedup.
+    expect(normalizePhone("'0690699699", 'FR')?.e164).toBe('+33690699699');
+  });
+
+  it('returns the country alongside the E.164 form', () => {
+    expect(normalizePhone('+33690699699', 'FR')).toMatchObject({
+      e164: '+33690699699',
+      country: 'FR',
+    });
+  });
+});
+
+describe('resolveCountry', () => {
+  it('returns null for empty / nullish input', () => {
+    expect(resolveCountry('')).toEqual({ iso: null, confidence: null });
+    expect(resolveCountry('   ')).toEqual({ iso: null, confidence: null });
+  });
+
+  it('exact-matches a canonical English country name', () => {
+    expect(resolveCountry('Anguilla')).toEqual({ iso: 'AI', confidence: 'exact' });
+    expect(resolveCountry('United Kingdom')).toEqual({ iso: 'GB', confidence: 'exact' });
+    expect(resolveCountry('United States')).toEqual({ iso: 'US', confidence: 'exact' });
+  });
+
+  it('matches case-insensitively', () => {
+    expect(resolveCountry('anguilla').iso).toBe('AI');
+    expect(resolveCountry('UNITED KINGDOM').iso).toBe('GB');
+  });
+
+  it('matches values with surrounding whitespace', () => {
+    expect(resolveCountry('  United States  ').iso).toBe('US');
+  });
+
+  it('handles diacritic variants of Saint-Barthélemy', () => {
+    // From real data: "Saint barthelemy" (#203), "St Barth" (#208), "Saint-Barthélemy".
+    expect(resolveCountry('Saint-Barthélemy').iso).toBe('BL');
+    expect(resolveCountry('Saint Barthelemy').iso).toBe('BL');
+    expect(resolveCountry('saint barthelemy').iso).toBe('BL');
+    expect(resolveCountry('St Barth').iso).toBe('BL');
+  });
+
+  it('resolves common abbreviations', () => {
+    expect(resolveCountry('USA').iso).toBe('US');
+    expect(resolveCountry('UK').iso).toBe('GB');
+  });
+
+  it('falls back to a city → country mapping for high-frequency cities', () => {
+    // From real data: "Kansas City" (#198), "Sag Harbor Y" (#239).
+    expect(resolveCountry('Kansas City').iso).toBe('US');
+    expect(resolveCountry('Sag Harbor Y').iso).toBe('US');
+  });
+
+  it('marks the confidence tier appropriately', () => {
+    expect(resolveCountry('Anguilla').confidence).toBe('exact');
+    expect(resolveCountry('Kansas City').confidence).toBe('city');
+  });
+
+  it('returns null + null for unresolvable values', () => {
+    // Migration script flags these for human review rather than guessing.
+    expect(resolveCountry('asdfghjkl xyz')).toEqual({ iso: null, confidence: null });
+    expect(resolveCountry('Mars')).toEqual({ iso: null, confidence: null });
+  });
+});