RFC 6238 says the verifier must reject a code it has already accepted: a code
stays valid for its whole thirty-second window, so one seen in flight — a
phishing page, a proxy, over the shoulder — could be replayed until it expired.
Tasks now record the counter of the last accepted step (totp_last_step), and a
login accepts a code only when its step is strictly greater. The guard is in the
UPDATE, not a read-then-write, so two logins racing with the same stolen code
cannot both find the old value and both proceed — exactly one moves the row.
auth.TOTPStep is VerifyTOTP that also reports which step matched, walking the
same one-step window; the code entered a little early or late spends the step it
was issued at, not the step it was checked at, so a late-but-valid code is still
single-use. Verified end to end: the same code presented to two logins in one
window is accepted once and refused the second time.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Bedt om som "abonnering af flere kalendere (ics og webcal?)". Det er også den
eneste vej for en privat konto: instansens OAuth-klient er Internal, og Google
afviser en konto udefra med `org_internal`, uanset hvad der ellers er sat op.
**Samme tabeller.** Et abonnement er én kalender med begivenheder i, og det er
præcis det, `calendars` og `calendar_events` allerede beskriver — med vinduet,
farven, `shown` og hele fejemaskinen omkring sig. En tabel til ville være en anden
vej til det samme sted, og to veje til ét sted er to steder at rette den dag noget
om begivenheder ændrer sig.
Det, der skulle laves om, var identiteten. En OAuth-konto er én pr. person og
udbyder — tokenet er identiteten — mens et abonnement er én pr. adresse, og man har
flere. `calendar_accounts_once` er derfor delvist nu: det holder for rækkerne uden
adresse, og et andet indeks holder adresserne unikke. Delvise indekser er den ene
ting, SQLite kan her, som ellers krævede en tabelombygning.
**`webcal://` skrives om til `https://`.** Det er ikke en protokol, noget taler —
det er en konvention, der får et skrivebord til at give adressen til
kalenderprogrammet i stedet for til browseren, og alle udgivere skriver deres links
sådan. At afvise den ville være at afvise folk på en teknikalitet.
**Adressen gennem `safedial`, begge halvdele.** Afvist hvor den skrives ned, så
den, der står med feltet, får svaret med det samme — og igen på den *opslåede*
adresse hver gang den hentes, fordi et navn, der blev godkendt ved indtastningen,
kan svare 127.0.0.1, når fejemaskinen kører klokken tre om natten. Det er den
sætning, `internal/safedial` selv står og advarer om, og den blev skrevet efter et
SSRF-fund i morges.
**Hentet én gang, før den gemmes.** En adresse, der ikke kan læses, er en tastefejl
langt oftere end en server, der tilfældigvis er nede, og at sige det, mens nogen
står med feltet, er de to sekunder værd. Et abonnement, der lydløst aldrig fyldes,
er den samme tavshed, notifikationerne havde.
Læseren er ny i `internal/ics`, som hidtil kun kunne skrive. To ting, den med vilje
ikke gør, står skrevet ved den: den udfolder ikke gentagelser, og den opløser ikke
tidszoner. Begge dele er større end de ser ud, og begge har ét sted at høre til
den dag de skal.
En ting, formatet lærte: DTEND er eksklusiv for en heldagsbegivenhed. Gemmes den,
som filen skriver den, dækker hver eneste helligdag også dagen efter sig.
Én adresse, der fejler, stopper ikke de andre. Et abonnement er en anden persons
server, og den ordinære tilstand for en anden persons server er, at den er i orden
indtil en morgen hvor den ikke er.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
To huller fra sikkerhedsgennemgangen, og de er samme historie fortalt to gange:
den ene kontrol, der findes til når adgangskoden allerede er tabt, kunne omgås af
netop den, der havde adgangskoden.
**H1 — spanden blev fyldt af adgangskoden alene.** `handleLogin` nulstillede
ratebegrænseren ved hver korrekt adgangskode, *før* den så på, om der var en
andenfaktor. Det gav én, der havde kodeordet, ubegrænsede portioner på ti gæt:
log ind, få en frisk spand og en frisk ventende session, brug ti gæt på koden, log
ind igen. Med tre gyldige koder i ethvert øjeblik og tyve forespørgsler i
sekundet er det lige odds inden for en eftermiddag.
Spanden ryddes nu først, når login er *færdigt*, og der er kommet en spand mere:
koder tælles pr. konto og ikke kun pr. adresse. Adressespanden er slået af enhver
med mere end én adresse, hvilket er det almindelige — en telefon og en bærbar er
allerede to. Det, der gør en sekscifret kode sikker, er at gæt er en knap
ressource, og knapheden skal tælles imod det, der bliver angrebet.
Den ventende session får lov at leve. At afslutte den ved første forkerte ciffer
blev overvejet og valgt fra: det ville koste en, der taster ét tal forkert, sin
adgangskode igen, og det køber næsten ingenting oven i loftet pr. konto.
**M3 — et lækket token kunne tilmelde sin egen andenfaktor.** `/auth/totp/setup`
lå kun bag `requireAuth` og spurgte om ingenting, mens `disable` altid har
krævet adgangskoden: døren åbnede med et token og lukkede kun med et kodeord. Et
stjålet token kunne hente hemmeligheden, lægge den i sin egen godkender, bekræfte
den og beholde den eneste kopi af gendannelseskoderne. Ejerens næste login ville
stoppe ved en kode, de ikke havde, og de kunne ikke slå den fra uden at logge ind
først. Et tyveri bliver til et lejemål — den sætning står allerede i filen ved
siden af om passkeys, og det er den samme regel.
Nu bag `requireSession` sammen med passkeys og sessionerne, og `setup` spørger om
adgangskoden ligesom `disable`. Symmetrien er pointen: at slå den til er mindst
lige så indgribende som at slå den fra.
Og en note kan oprettes inde fra et projekt. At ligge i et projekt *er* måden en
note deles på, så det er én handling frem for to — man skulle før oprette noten
under Noter og bagefter finde projektet frem i "Del i". Ruden findes nu, også før
der er en eneste note, for ellers er der ingen knap dér, hvor man opdager at der
skal skrives noget ned.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
A password and a TOTP code are both shared secrets: the server keeps something
that can be stolen from it, and the person keeps something that can be talked out
of them. A passkey is neither. The private half never leaves the device, and the
signature is bound to the origin that asked for it — so a convincing copy of the
sign-in page at another address gets a signature it cannot use.
Logging in asks for no email. The device knows which account its key belongs to,
which is not only convenience: it means the sign-in page cannot be used to find out
who has an account here. A key that verified its owner is both factors at once and
completes the login; one that only proved possession still meets the TOTP step,
exactly as a password does.
The relying party id is derived from VERDANDE_BASE_URL rather than configured
separately — a second setting that has to agree with the first is one that will
one day disagree, and the failure is a login nobody can complete. An IP address is
refused up front: no browser accepts one, and without the check the server issues
a challenge happily and the browser throws SecurityError long afterwards. The list
endpoint reports whether this deployment can offer them at all, so the interface
never shows a button that cannot work.
A challenge is stored server-side, answerable exactly once, and taken rather than
read — two requests racing the same one would both succeed, which is the shape of
a replay. A sign count that has gone backwards means the credential was cloned and
is refused rather than logged.
The Go tests cover who may reach these endpoints and that challenges are spent.
The ceremony itself needs an authenticator, so the smoke test drives Chromium's
virtual one over CDP — the only thing that can tell whether the base64url
conversions are right, since one wrong byte produces a signature that will not
verify and reads as a broken key rather than a broken encoder.
That test runs at localhost in its own context while the suite stays on the
loopback address, because WebAuthn refuses an IP and resolving localhost is slow
enough here to cost the suite minutes.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
`last_seen_at` has been written on every request since sessions existed —
throttled to once a minute, deliberately, so a list could one day say
"denne enhed, lige nu" — and nothing has ever read it. The store even had
ListSessions. What was missing was two routes and a panel.
GET /auth/sessions lists them, most recently used first, with the current
one marked so nobody has to work out which row is the browser they are
reading it in. DELETE /auth/sessions/{id} ends one. Ending the current
session is allowed and is simply logging out: refusing it would be a rule
with no reason behind it, and somebody clearing every device wants this
one gone too.
Both are behind requireSession rather than the ambient auth, the same as
the API tokens. A leaked token that could list its owner's devices and end
their sessions turns a theft into a lockout.
The delete is scoped in the statement rather than checked and then run.
An id read in one step and deleted in the next is a window, and the whole
reason somebody is on this screen is that they think another person is in
their account.
The device names are a handful of substring tests, not a parsing library.
The question this answers is "is one of these me?", and for that a wrong
guess between two Chromium forks costs nothing while a dependency that has
to be kept current costs something every year. Order is the whole
correctness of it: an iPhone's user agent says Mac OS X, Edge says Chrome,
and Chrome says Safari. The raw string is sent alongside and sits in the
row's title, so anything the summary gets wrong is still visible — and
something that is not a browser at all shows its own name rather than
"Ukendt", because a CalDAV client is a real session.
Times are relative. The question is "was that me, just now?", and an
absolute timestamp makes the reader do the subtraction; past a week it
switches to a date, because "for 23 dage siden" is a number nobody can
place.
The smoke test signs in a second time in a second browser context, ends
that session from the first, and checks the other browser is really signed
out — and that this one is not.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
authenticate() cannot tell "no such session" from "the session lookup
failed" on its own — both arrive as an error. Answering 401 for both
meant a disk or file-permission problem presented as every session
ending at once: the frontend clears its state and shows the sign-in
screen to everybody, and the logs record a wave of failed logins rather
than the fault.
Now only a missing or unknown credential is 401. Anything else is a 500
and is logged as what it is.
Found while writing the smoke tests, where a deleted database file
produced SQLITE_CANTOPEN on the connections that had not been opened
yet — so most requests succeeded and a few reported the user as signed
out, which reads exactly like a flaky auth bug.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Gmail now connects. Authorisation-code flow with PKCE, the verifier kept
server-side rather than in a cookie — the callback is a top-level
navigation from Google, and a SameSite=Lax cookie is the kind of thing
that works until a browser tightens its defaults. State is checked, the
attempt expires after ten minutes, and the spent verifier is deleted
rather than left at rest.
Scope is gmail.readonly and the sync is one-way on purpose. Unstarring a
message does not delete the task; completing the task does not touch the
mailbox. Two-way would mean deciding what happens when both sides
changed, and the only honest answer is a sync model far larger than the
feature. The query carries newer_than:30d so connecting an account with
a decade of starred mail does not create a decade of tasks.
The update check is off unless the operator turns it on, asks GitHub at
most every six hours, and sends nothing about the instance — no
identifier, no version, no counts. A development build never reports an
update: somebody running their own tree is ahead of every release, and
telling them otherwise trains them to ignore the notice. Only
administrators see it, because only they can act on it.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Completes the MVP surface: project and section CRUD, task CRUD with
sub-trees, drag-and-drop ordering, the quick-add endpoint over the
natural-language parser, Today and Upcoming, search, sharing with roles,
an activity log and a WebSocket for live updates.
Permission checks are route middleware rather than a first line in each
handler, so an endpoint is guarded by where it sits instead of by the
author remembering. Anything the caller may not see answers 404, never
403 — a 403 confirms the thing exists. Visibility is enforced inside the
list query, so another user's project cannot be reached by filtering or
searching at it.
Ordering is a float, so a drop writes one row instead of renumbering the
list. When repeated drops into one gap exhaust the precision, the
section is spread out again and the move retried — in a separate
transaction, since the attempt that discovered the problem rolls back.
The connection pool is not 1: a single connection makes the pool a lock,
and a query run while an earlier result set is still open then waits for
a connection it is itself holding. The store now closes its rows before
querying again, and the pool leaves that mistake slow rather than fatal.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Sessions are stored as hashes, so a database dump contains nothing that
can be pasted into a browser. A login that has passed the password but
not the second factor is modelled as a pending session: it expires, is
revocable, and reaches exactly one endpoint.
Signup is invite-only and takes the email address from the invite rather
than the form, so a link cannot be redirected to somebody else. The
first admin is created by an endpoint that refuses once any account
exists, checked and inserted in one transaction because it is
necessarily unauthenticated.
Login failures and forgotten-password requests answer identically
whether or not the address has an account — otherwise the form is an
account-existence oracle. Password rules are a length floor and nothing
else: composition rules push people towards worse passwords.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
