1. Summary of changes
Password auth → email OTP, everywhere it existed for the tenant/business app: sign-in, customer self-registration (/register), staff-invitation acceptance, and the installer's administrator step. Flow is always: email → 6-digit code emailed → code entered → session created, via one shared service (otp.service.ts) reused by every entry point.
NextChair Manager's own auth was not touched — this only affects tenant-side (business admin/staff/customer) authentication, per the spec's explicit instruction.
Installer improvements: Step 2 (Administrator) now asks only Name + Email + optional Phone, verified inline via the same OTP widget (no redirect). Step 3 (Business Details) pre-fills Business Name from the Manager-provisioned BUSINESS_NAME, shows the booking URL (NEXT_PUBLIC_APP_URL) as a read-only info box instead of asking for it, and has a distinctly-labeled "Business Website (optional)" field with copy clarifying it's not the booking URL.
Installation cannot complete with an unverified admin email — enforced server-side (finalizeOtp runs inside the same DB transaction as user/business creation), not just trusted from client state. A mid-wizard refresh still can't create duplicate admins or partial records — that property was preserved by design, not incidentally.
2. Prisma/database changes
New EmailOtp model (email as PK — one row per address, so a new request naturally invalidates the previous code): codeHash, purpose, expiresAt, attempts, verifiedAt, consumedAt, timestamps. Only a bcrypt hash of the code is ever stored.
User.passwordHash — unchanged schema (already nullable), just annotated as deprecated. No destructive migration; historical rows are untouched.
Migration: prisma/migrations/20260905190022_email_otp_authentication — adds EmailOtp only. Generated and applied against throwaway containers only; the real next-chair-mysql production database was never touched (confirmed not even running on this host during this session).
3. New environment variables
None required for production. One new variable, E2E_TEST_MODE, exists purely for the Playwright suite (set only in playwright.config.ts's webServer.env) — it unlocks a /api/test/otp-code debug endpoint and bypasses OTP rate limiting so the same seeded users can sign in dozens of times across one test run. It must never be set on a real deployment; nothing in the app sets it anywhere else.
4. Email delivery configuration
Nothing new to configure. OTP emails reuse the existing EmailProvider abstraction and EMAIL_PROVIDER env var exactly as configured today — console in dev (prints to server logs), brevo in production via the same SMTP credentials already documented. The OTP email is a new template (otp-email.ts) sent directly (bypassing the async notification/cron pipeline, since a 10-minute-expiry code can't wait for a delivery retry loop).
5. Migration considerations for existing users/installations
Existing users lose password sign-in — the only way to authenticate now is email OTP. There is no in-app fallback; this is an intentional, sharp cutover. If existing customers/staff/admins need advance notice, that's a business/communications decision outside this change.
No account data is deleted or migrated — passwordHash rows are simply never read for auth anymore.
prisma/seed.ts / scripts/ensure-super-admin.ts still set a passwordHash for seeded dev users — harmless and vestigial now, not cleaned up (flagging it rather than touching seed data silently).
Installations already completed are unaffected; only new installer runs go through the OTP admin-verification step.
6. Files changed
New:
src/lib/auth/otp.service.ts — the core requestOtp/verifyOtp/finalizeOtp service
src/lib/auth/__tests__/otp.service.integration.test.ts
src/services/notifications/templates/otp-email.ts
src/features/auth/components/otp-code-step.tsx — shared code-entry UI
src/features/auth/actions/request-sign-in-otp.ts
src/app/api/test/otp-code/route.ts — e2e-only, gated on E2E_TEST_MODE
prisma/migrations/20260905190022_email_otp_authentication/
Modified — auth core: prisma/schema.prisma, src/auth.ts, src/features/auth/schemas.ts
Modified — sign-in/register/invitations: sign-in-form.tsx, register.ts, register-form.tsx, accept-invitation.ts, accept-invitation-form.tsx, staff-invitation.service.ts
Modified — installer: installer.service.ts, schema.ts, install.ts, install-wizard.tsx, install/page.tsx, installer.service.integration.test.ts
Modified — email / e2e infra: console-email-provider.ts, playwright.config.ts, e2e/helpers.ts, and the four e2e/*.spec.ts files (dropped the now-unused password argument from every signIn() call).
7. Verification performed
npx tsc --noEmit, npm run lint, npm test (276 unit) — all clean.
npm run test:integration (207 tests, throwaway DB) — includes 11 new OTP-service tests and a rewritten installer suite; a genuine race condition in requestOtp (concurrent requests for a brand-new email double-hitting the upsert's create branch) was caught and fixed here.
Full npm run test:e2e against a fresh throwaway database: 36/37 passed. The one failure (owner-journeys "opening hours conflict" test) is a pre-existing, auth-unrelated ordering flake — appointment-count ambiguity from earlier tests' bookings — not something this change touches or introduced.
Live manual verification in-browser: existing seeded customer sign-in via OTP; new customer registration via OTP (session created, landed on Home); installer wizard end-to-end through Step 3, confirming email-verification gating, Business Name pre-population from BUSINESS_NAME, and the read-only Booking URL / distinct Business Website fields.
All throwaway Docker containers/DBs used for this work have been removed; the real production database was never touched.
Phase 5 is complete. All 53 tasks are done, verified on a fresh database in a single clean run: **121 unit tests**, **55 integration tests**, and **15 E2E journeys** (6 Phase 4 + 9 new Phase 5) all passing, plus a clean `tsc`/`eslint`/`build`.
Summary of this final stretch:
- **Fixed a real bug**: `StaffService`'s break/time-off update/delete functions threw uncaught instead of failing gracefully on a permission mismatch — fixed with proper `PERMISSION_DENIED` handling, covered by new integration tests.
- **Built the remaining Phase 5 UI**: Breaks editor, Time Off editor, Barber Profile, and Notification Preferences — all wired to real services, no placeholders.
- **Extended seed data**: more customers, loyalty accounts/transactions/rewards, and appointments spanning every status today (anchored to real time so the "Current Appointment" priority logic is reliably exercised).
- **Found and fixed a second real bug live in the browser**: the Break/Time-Off edit sheets showed stale default values instead of the item being edited (a classic `useState`-doesn't-reinitialize-on-prop-change bug) — fixed with a `key` prop to force remount.
- **Wrote the full Phase 5 test suite**: unit tests for `selectCurrentAppointment` and all `StaffService` validators, integration tests for `LoyaltyService` and `StaffService` (including the permission-fix regression tests), and 9 new Playwright E2E journeys covering the brief's exact required list.
- **Did the desktop-responsive pass**: a persistent sidebar nav replacing the bottom bar at `lg:`, a genuine calendar+"Right Now" side-by-side split, and 2-column layouts for the clients list and customer details — addressing the brief's explicit "more than simple centering" requirement.
- **Wrote [docs/phase-5-summary.md](docs/phase-5-summary.md)** documenting everything above in full.
Nothing is committed — the whole session (Phases 2–5) sits uncommitted on top of the initial template commit, same as you left it. Let me know if you'd like me to commit, or if you want to move on to Phase 6.
Seed data extended with a second barber (different hours/services), a beard-trim service + category, breaks, time off, a guest customer, and appointments in all three key states — verified against a live throwaway Postgres.
14 new integration tests (38 total with Phase 3's) covering guest/authenticated booking, any-barber assignment, slot-conflict handling, ownership enforcement, guest-data isolation, and book-again repricing.
Playwright E2E suite for the 6 required customer journeys, with its own global-setup.ts that migrates and seeds a database automatically.
Full verification pass, which caught and fixed three real bugs along the way (not just test-workarounds):
A date off-by-one bug in the calendar picker that made real weekdays show as closed for anyone in a UTC+ timezone (including the business's own).
A dialog that could vanish mid-confirmation on cancellation, before the customer could read the late-cancellation notice.
A silent test-cleanup leak in the Phase 3 fixtures that had been leaking stray businesses since Phase 3.
Plus a baseline desktop-responsive fix (centered max-w-2xl columns) across Home/Appointments/Settings/booking flow, since desktop had been effectively unstyled.
Final state: 90 unit tests, 38 integration tests, and all 6 E2E journeys passing together on a fresh database; clean tsc, eslint, and next build. Full writeup with routes, security model, guest-matching rules, known limitations, and what to check before Phase 5 is in docs/phase-4-summary.md.
Stefan Lazic