Indstillingerne er ti faner med syvogtredive afsnit, og den eneste vej til et
bestemt af dem var at huske, hvilken fane det lå under. ⌘K kunne opgaver,
projekter og noter — alt det, man selv har skrevet, og intet af det,
programmet består af.
Ét indeks, to steder det bruges: et felt øverst i indstillingerne og paletten.
To lister over de samme afsnit ville være to steder at glemme et nyt et.
Overskrifterne står ikke i indekset. Hver post peger på den nøgle, afsnittets
egen overskrift allerede bruger, så et afsnit, der bliver omdøbt, følger med af
sig selv, og søgningen kan begge sprog uden at kende nogen af dem.
`words` er derimod skrevet i indekset, og det er med vilje: det er søgeord,
ingen får at se. Det danske afsnit hedder "Tælling af installationer", men det
ord, man kender det ved, er "beacon" — og på samme måde 2fa, imap, webcal,
webhook. De er de samme på begge sprog, hvilket er hele grunden til, at de
virker som søgeord.
Ankrene er nye id'er på afsnittene. Tre af dem stødte sammen med et felt inde i
afsnittet — to ens id'er gør <label for> tvetydig og getElementById tilfældig —
og hedder derfor to-faktor, kalenderfeed og caldav-server.
Springet dertil kan ikke overlades til browseren: siden hentes af ruteren, og
afsnittet findes først, når dens data er hjemme. Der prøves i to sekunder og
gives så op. Blinket bagefter er ikke pynt — man er landet midt i en side med
otte afsnit, man ikke selv rullede hen til.
Prøverne læser filerne frem for at klikke: halvdelen af afsnittene vises kun
under en betingelse, så en prøve, der ledte efter dem i en browser, ville melde
fejl på det, der med rette var skjult.
Og palettens pladsholder sagde "Søg i opgaver og projekter". Den har kunnet
noter længe, og kan nu også indstillinger.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Ønsket var en liste over de installerede browsere. Den findes ikke: en
webside kan hverken se, hvilke browsere der er på maskinen — listen er
lukket land, fordi den er et fingeraftryk, der ville følge folk rundt på
nettet — eller bede systemet om at bruge en bestemt af dem.
Det eneste håndtag er de URL-skemaer, browserne selv registrerer:
firefox://open-url, googlechrome://, microsoft-edge:. Dem kan man prøve,
og man kan ikke spørge, om de findes. Så indstillingen er skrevet som
det, den er — et forsøg med et faldback — frem for som et løfte, der
ville holde på telefonen og ikke på en Mac.
Valget står i localStorage, ikke på kontoen. Samme grund som
sidebjælkens bredde: det er en egenskab ved maskinen, man sidder ved.
firefox:// virker på telefonen og gør ingenting på Mac'en, så et valg,
der fulgte kontoen, ville være forkert det ene af de to steder hver gang.
Ét sted i koden frem for ét pr. komponent. Links står i opgavetitler, i
beskrivelser, i noter og i indstillingerne, og en regel, der skulle
gentages hvert af de steder, ville mangle det ene sted, ingen tænkte på.
Kun udadgående links; programmets egne ruter går gennem SvelteKit som før.
To ting, målingen rettede undervejs:
Det skjulte iframe — den kendte opskrift — bliver blokeret af appens egen
Content-Security-Policy, som siger default-src 'self'. Uden e2e-prøven,
der fangede CSP-fejlen i konsollen, ville skemaet aldrig være blevet
forsøgt i produktion, og indstillingen ville have set ud til at virke,
fordi faldbacket åbnede linket alligevel. Nu sættes location i stedet:
et ukendt skema afbryder navigationen frem for at forlade siden.
Og faldbacket troede sig blokeret hver eneste gang. window.open med
noopener returnerer altid null — det står i specifikationen — så
kontrollen af, om fanen blev åbnet, faldt altid ud til "blokeret", og
den aktuelle fane blev navigeret væk i stedet. Håndtaget er det eneste,
der kan kende en blokeret fane fra en åbnet, så det bruges nu, og opener
ryddes bagefter.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The setup screen showed the secret and the otpauth URI as text and asked
you to scan — with nothing to scan. It renders the URI as a QR now, an SVG
(one dark path on a white card, so it reads in either theme) generated from
the barcode encoder already in the module graph via pquerna/otp. The secret
stays below it for a device that cannot scan.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The sidebar read as muted 13px; the menu items now use their own size at
medium weight so they carry at a glance (Todoist-ish). Both sizes are
choices under Settings → Appearance:
- Menu font size drives a dedicated --menu-size the sidebar uses.
- Body text size re-scales the shared type tokens (the list and the notes),
the same mechanism a look uses.
The two are independent on purpose — one is a glance down a list of names,
the other a paragraph you read. Kept in localStorage like theme and look,
and applied in app.html before first paint so a chosen size does not flash
in and resize. Four steps each (Small/Default/Large/Largest); Default
carries no attribute so the base tokens stand.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
A donate link belongs in Settings and nowhere in the way — so it sits last,
understated, below the device list. A plain anchor with an inline SVG cup:
no third-party script, no webfont, no tracking, so it works offline and
cannot phone home. Wording says the app is MIT with nothing held back and
that nothing changes if you don't pay.
Co-Authored-By: Claude Opus 4.8 <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>
Fire udseender ved siden af de fem temaer: Verdande, Rolig (serif, mere luft),
Tæt (flere rækker, mindre luft) og Terminal (én bredde til det hele). De ganges ud
til tyve udseender fra otte små blokke CSS frem for at kræve en blok hver.
To akser, fordi det er to spørgsmål. Den, der vil have en serif om natten, skal
ikke opgive den mørke palet for at få den — og prøven holder netop det fast: at
vælge en skrift må ikke trække temaet med sig.
Udseendet sættes før første optegning, ligesom temaet. Ellers bliver siden sat op
i én skrift og derefter i en anden, og det er et synligt spring.
Det er også det ærlige svar på at ligne noget andet. Standarden er bevidst
genkendelig — det var det, der blev bedt om — men et program med ét muligt
udseende har lånt en form, det ikke kan give tilbage. Med udseender er ligheden en
indstilling blandt flere frem for det eneste, det kan være.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Reported from use: "Fetch now" said "something went wrong" and the error log was
empty. Both halves were the same bug wearing two hats.
`handleGmailSyncNow` answered 502 with the code `internal_error`, which the
interface maps to a generic sentence — so Google's own words, which are the whole
diagnosis, were replaced by one that says nothing. And `writeError` records
nothing; only `s.internal` does. So there was no message to read and nowhere to
look it up afterwards.
`s.upstream()` is the answer: 502 because this is somebody else's service saying
no rather than this server breaking, a code of its own so the interface can quote
what was said, and a row in the error log — which is the entire reason that log
exists. A Gmail sync failing quietly for a week is otherwise invisible: the
background job writes a line the next restart erases.
The same connection also left the mailbox unnamed. The address is learned at
connect time and that call can fail; a warning went to the log and an empty string
to the database, so the page said "an unknown account" and kept saying it. The only
way back was to disconnect and reconnect, which nobody would guess. The status
endpoint asks again when it finds none, so a wrong answer lasts until the next look
rather than until somebody reconnects.
Ten Danish strings were hiding in `confirm()` and `app.toast()` calls, including
every destructive confirmation in the app — the worst possible set to leave in one
language, since it is what somebody reads in the half-second before agreeing to
lose something. The i18n guard reads markup and attributes, and a string argument
lives in the script block. It reads those now, and found four my own grep missed.
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>
The account has had a `locale` since the beginning and it only chose which grammar
quick add read a line with — so picking English changed nothing anybody could see,
and the field said so honestly: "Sprog i hurtig tilføjelse". It says "Sprog" now,
because it means it.
Every component goes through `t()`. Danish is the source: a key missing from
English falls through to Danish rather than to the key, because a Danish sentence
in an English screen can be read and `settings.notifications.title` cannot.
`tag()` is the single place `Intl` is asked. Before, `'da-DK'` was written into a
dozen components, and that is the half of a translation that gets left behind — an
English interface still saying "24. aug." is exactly the shape of a job half done.
There is a smoke test that switches to English and refuses to see a Danish month
name in the calendar's heading.
Colour and theme names are keys now. `colors.js` keeps its ids untouched — they
are what the database stores, and `internal/store` reads them out of that file —
but `name` is `'color.tomato'`, resolved where it is drawn.
The Inbox keeps its name. It is a project row the server creates at signup, not a
string in the interface, and it can be renamed like any other project.
Four copies of "3 hours ago" became one, in `web/src/lib/when.js`. They had
already drifted: one said "aldrig logget ind", another "aldrig", and two stopped
at days where the others carried on to a date.
Routes stay Danish. `/indstillinger`, `/projekt`, `/uddelegeret` are bookmarks and
they are in every smoke test; translating them buys nothing and costs both.
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>
Two themes and a toggle between them. Now five, chosen from a grid under
Settings → Konto: the two that existed, a warm dark (Skumring) with amber
where the green was, a warm light (Papir), and a high-contrast one.
Each swatch is painted in its own theme rather than described, so the
choice is made by looking. data-theme sits on the swatch and not on the
card — it redefines --ink too, and a card wearing a dark theme's ink on a
light page has a name nobody can read.
Every theme states its full palette rather than inheriting and patching.
A partial theme looks finished until somebody adds a token, at which
point four themes silently fall back to a colour from a fifth. That is
also why the dark palette is repeated under [data-theme='dark']: :root
carries it as the default and :root only ever matches <html>, so a swatch
asking for it by name would otherwise show whatever the page was wearing.
The theme-color meta is updated too, so an installed PWA's frame and a
phone's address bar follow rather than staying whichever colour shipped
in the markup.
Contrast measured for all five. The new ones clear 4.5:1 down to the
quietest tier — which is where dates and counts live, and the first thing
to disappear. Kontrast reaches 8.9:1 there. The two original themes are
left as they are: their faint ink sits at 3.1–3.8, which is worth
revisiting, but not as a side effect of adding colours.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
There was no /indstillinger route at all. The Gmail OAuth callback
redirects there and had been answering 404 since it was written.
Six pages rather than one long scroll, because the sections have nothing
to do with each other and somebody opening API tokens should not have to
walk past their own password to get there: the account and its second
factor, notifications, integrations, AI, tokens, and data. Everything
listed as having no interface in the handoff is reachable from one of
them — the calendar feed, the mail-to-task address, Gmail, the AI
provider, import, export, templates and the update notice.
Two decisions worth naming. The AI key field starts empty and says why:
a settings page that repopulates a password field is one that will
eventually leak a key into a screenshot, and an empty value means "leave
the stored one alone" rather than "clear it". And the form chrome lives
in the layout as :global rules, because scoped styles do not reach a
child route and six copies of the same twelve selectors is six places for
them to drift.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
