A guardian with a fresh second factor mints a one-time handover link (hlp_ token, HMAC hash stored only, 1/7/14 days, at most one open per profile, withdrawable) with a proposed access level per guardian: end, view only or manage, view only by default. The link is shown once with a copy button and a QR code; nothing is mailed. The panel sits at the end of each managed-profile row and hints when the person is under 16. The person opens /claim/<token>, sees a minimal preview (name, expiry, who keeps which access, no health data) and chooses a username, a required email and a password under the registration policy. The claim is one transaction under the managed-profile lock: the token is consumed, the credentials are set, the marker is cleared, every pending invitation the record offered is withdrawn, each guardian's access is set to its proposal, the disclaimer, onboarding and AI consent are reset, and every step is audited on the record and on each guardian's own account. A failure anywhere leaves the profile managed and the link unused. Each guardian is notified on their own channels. The new owner then sees each guardian's access on the first screen after signing in and decides finally; until then the proposal holds, and the decision waits at the top of Shared access. A guardian whose access moved since the claim is left alone. The same screen points the owner at their own notification channels, since reminders no longer reach the guardians. Both anonymous routes refuse a single-sign-on-only instance, refuse a live session before spending the per-address rate limit, check the link before probing names, and answer one 404 for every unusable token. The token travels in request bodies only; hlp_ joins the redaction and secret-shape rules and /claim/ the path-secret registry. Usernames starting with managed- are reserved. The session-surface and acting- account guards list the new surfaces with their reasons.
e2e/
End-to-end browser tests. Playwright 1.60 drives a production build of the app against a real PostgreSQL, with @axe-core/playwright for accessibility assertions. This is the heaviest test tier; CI runs it on every PR, and locally it is worth running when a change touches a UI flow.
Running
pnpm e2e
The Playwright config (../playwright.config.ts) builds the app (next build) and brings up Postgres before the specs run; setup/global-setup.ts seeds the auth + fixture state. The suite is not part of the fast local gate (typecheck / lint / test) — it surfaces at PR CI, so expect responsive/wizard/nav reworks to flag here first.
Layout
setup/—test.ts(the suite'stest+expectentry point),global-setup.ts(auth + DB seeding),test-helpers.ts(shared login + navigation helpers).utils/— fixtures such asmock-dashboard-snapshot.ts.fixtures/— synthetic payloads a journey uploads, built in code rather than committed as blobs so the content stays reviewable (apple-health-export.ts).*.spec.ts— one spec per flow: auth/login/redirect, dashboard, charts, the medication-wizard cadences (medications-wizard-*), insights generation + scroll restoration, doctor report, settings, mobile-viewport consistency, locale switch, accessibility (a11y.spec.ts), and thev1427-*regression set.
Conventions
Import test and expect from ./setup/test, never from @playwright/test — types (Page, Route, …) still come from the package. The entry point extends Playwright's test with an automatic fixture that drops route handlers and page listeners after every test, so a handler left in flight cannot fail the test it belonged to once the context closes. src/__tests__/e2e-route-cleanup-guard.test.ts enforces the import boundary.
Assert against stable data-* attributes (data-slot, data-display-step, root display attrs), not viewport-dependent visible text. Responsive sm:hidden UI changes break getByText on desktop while the underlying element is still present — anchoring on data attributes keeps the specs stable across breakpoints. See ../CLAUDE.md.