Typing [[ did nothing. The toolbar hint offered "[[ another note" and the parser
turned a fully-typed [[Title]] into a link on save, but the completion that makes
it usable — the one # has for projects — was never there, so you had to know and
type a note's title exactly, brackets and all.
Now [[ opens the same picker # does, over the notes the page has loaded: the
current note is left out (a note linking to itself is a loop nobody meant), and
one without a title yet cannot be pointed at. Choosing a note closes its own
brackets — the opener is already in the text — and leaves a space, so the next
word is a word and not more of the tag. On save the link is real and shows in the
note's links, not merely as text.
The picker's two kinds are told apart where a project wears its colour: a note
suggestion wears the brackets that open it.
e2e: [[ offers a note by title, choosing it writes [[Title]] into the note, and
the link lands in the note's links. Full Chromium suite green.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The landing page did not mention two things the app grew — sharing a note with a
person, and task durations — and its screenshots were all in the dark theme.
- Copy: a cell for sharing a note or a page (to a person, or by filing it in a
project, with the Shared with me group), and one for how long a task takes (drawn
to length on the calendar, dragged by its foot, kept when moved).
- Two new screenshots in the light theme, at the top of the gallery: the calendar
drawing timed tasks to their real length, and a note somebody shared gathered
under Shared with me. English throughout, like the rest of the site — the capture
account is English, so the interface is.
The generator grew the demo data these need: a handful of timed tasks with lengths
across the week, and a note the colleague shares back to the owner. Every other
screenshot was recaptured from the current build in the same pass, so the whole set
reflects what ships today (the tidied note footer, and the rest).
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
A timed task was drawn at a fixed half hour whatever its `duration_min` said, so a
length the data model already carried was invisible and uneditable. Three parts:
- The calendar draws a task at its real length — a quarter-hour floor so a
zero-minute task is still grabbable, the day's end as the ceiling — instead of a
flat thirty minutes. A ninety-minute task now looks like ninety minutes.
- A grip along the foot of a timed task drags its length. Pointer events, not the
HTML5 drag the body uses, and stopPropagation between them — otherwise making a
task longer would pick it up and move it instead. It snaps to the quarter hour,
follows the handle live, and writes once on release through a new store `resize`.
Moving a task (the existing day/time drag) leaves the length alone.
- The task drawer gains a length field beside the time — minutes, shown only with
a time to hang it on, since a duration without a start is a length of nothing and
the calendar has nowhere to draw it. So a length can be set off the calendar too.
e2e: dragging the foot of a task makes it longer both on screen and in what the
server stores, and the time does not move. Full Chromium suite green.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The sharing controls were laid out across the note's footer — the project select,
the whole "Del med personer" panel and the Save/Delete buttons all on one row. It
crammed: "Læg i projekt" wrapped to two lines and the people panel ran into the
rest.
Now one Del button in the footer opens a popover that holds both ways a note is
shared — a project and named people — stacked in a small card. The footer is a
status on the left and Del / Gem / Slet on the right, and nothing wraps. The
button carries a count when the note is shared with someone, so "shared" is
legible without opening it.
The popover closes on a click outside, on Escape, and on switching to another
note — the last tracked by note id, so a save returning a fresh copy of the same
note does not slam it shut mid-use. The inner "add someone" button is now Tilføj,
so it does not read as a second Del.
e2e updated to open the popover before reaching the controls; full Chromium suite
green.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
A <pre> is preformatted, so the browser answered Enter by inserting a <br> and
keeping the caret inside it. A monospace last line therefore trapped everything
typed after it in monospace, with no way back to body by typing — and the style
menu could not get out either: `formatBlock('p')` on a line inside a <pre> nests a
<p> *inside* the block (`<pre>…<p>body</p></pre>`), so the text stayed monospace
and the note was left malformed. Reported as "monospace keeps going and I can
neither delete it nor switch to body".
Two fixes, both in the editor:
- Plain Enter in a <pre> now steps out: the tail after the caret becomes a
paragraph below the block, and that is where the caret lands. Shift+Enter is
untouched, so a soft line break still writes multi-line code inside the block —
Enter to leave, Shift+Enter to stay.
- The style menu converts anything touching a <pre> by hand, replacing the element
rather than reformatting inside it, so a monospace line goes cleanly back to body
(or to a heading) instead of nesting.
The split can leave an empty text node in the new paragraph, and a block with no
element and no text is not a caret host in Chromium — the next keystroke falls back
into the block above. So an empty paragraph is given a <br> to stand in, which was
the difference between the caret landing in the new line and the text reappearing
in the code.
e2e: a monospace line left on Enter is body after it, Shift+Enter stays monospace,
the menu returns it to body, and the whole thing survives the round-trip through
Markdown and a reload.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The calendar test asserted `[data-date=day] .tevent` had a count of exactly one —
the mocked meeting — after dragging its task to the next day. That count assumed
the day held nothing but this test's own events. It does not: the suite shares one
database, and an earlier test drags a task across a month boundary, which on some
dates lands a timed task on this very day. A timed task renders as a `.tevent`
too, so the count was two, and the test failed — but only in the full run, and
only when the date arithmetic put the two tests on the same cell. Alone it passed,
which is exactly the shape of a shared-state collision rather than a real bug.
Named, not counted: assert the meeting is still there and the task is no longer in
the day's column, which is what "the events stayed, the task moved" actually
means — and is true however full another test left the day. Same for the all-day
band. No product code changed; the drag and everything it checks are untouched.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The project-filing control was relabelled "Del i" → "Læg i projekt" and its empty
option "Kun mig" → "Intet projekt" (a note can now be shared with people while
under no project, so "kun mig" was no longer true). The two e2e tests that drove
that control by its old label are updated to the new one.
And a new test for the feature itself: an owner shares a note with a second
account from the Del med personer panel, the recipient's own list grows a Delt
med mig group with the note in it, a viewer's row carries no star or archive
control, and unsharing takes it back off their list. The recipient is navigated
on the origin the invite signed her in on — VERDANDE_BASE_URL is localhost while
the suite drives 127.0.0.1, and a session cookie set on one host is not sent to
the other.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Until now a note was shared exactly one way: file it in a shared project, and
everyone who could read the project could read the note. That is right when the
note belongs with a body of work and wrong when it is just "let Sofie see this" —
it made you stand up a project to hand over a single page.
A note can now be shared with named people directly, at viewer or editor — the
same two roles a project membership uses, so there is one idea of a role in the
program and not two. The paths stack: a note can be loose, filed, shared with
people, or any mix, and access is the most any of them allow.
The store:
- note_shares (migration 0030): note ↔ user ↔ role, one row per person, owner
recorded. Visibility (AllNotes, and search via mayTouchNote) widens to include
notes shared directly with the reader.
- the effective role folds a direct share on top of the owner and project paths.
The rules, drawn where they protect the owner:
- read = viewer, edit text = editor, on any path.
- MOVE a note (change its project) is owner-only: an editor filing it into a
project the owner is not in would take the owner's own note away from them.
- DELETE is owner or project-editor — a direct share, however high its role,
does not reach to throwing the note away.
- SHARE and UNSHARE are the owner's alone, like a project's invitations.
- the picker is everyone on the instance (a closed, invited set) minus who is
already on the note; a made-up id and the owner themselves are refused.
The list:
- a "Delt med mig" group at the top, collapsible, that appears only when it has
something in it — the same rule Favoritter follows — so it costs nothing when
you share nothing. A shared note lives there, not also in a time bucket.
- every shared note carries a small chip in its owner's avatar colour, the
project mark's shape said for a person.
- no star or archive button on a note somebody else owns: those change the note
itself, and it is not yours to put away.
- the editor grows a "Del med personer" panel for the owner: who can see it, at
what role, and an add row drawn from the instance's other people.
The old comment in the notes footer argued against a note having an access list
of its own. That was the right call until the case it did not cover — sharing
without a project — turned out to be the one actually asked for. Updated to match.
Person now carries json tags, so a note's owner serialises as id/name/avatar_color
like every other person in the API rather than as Go field names.
Tests: a shared note reaches the other person marked and owned; a viewer reads but
cannot write; an editor writes but cannot re-share or delete; unshare removes
access and is owner-only; the candidate list excludes who is already on and the
owner; and a made-up id and self are refused. OpenAPI covers the three new routes.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
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>
The rate limiter and the audit log key on the caller's address, and that address
was read with chi's middleware.RealIP — which believes X-Forwarded-For from
anyone. So a caller could set it to a new value on every request and get a fresh
password-guess bucket each time, and could write any address they liked into the
log the panel's watchers read. The one control meant for when a password is
already gone was keyed on a number the attacker got to pick.
Now the header is believed only when the machine that *connected* is a trusted
proxy — by default anything on a private network, which is the shape of a reverse
proxy or tunnel sharing the host or the docker bridge. A connection straight off
the internet is trusted for nothing and is keyed on the address it actually came
from. VERDANDE_TRUSTED_PROXIES overrides the set (CIDRs, or "none" to trust no
proxy at all); VERDANDE_REAL_IP_HEADER names the header.
Verified in the current deployment before the change: behind the Cloudflare
Tunnel a spoofed X-Real-IP already got no fresh bucket, because cloudflared
overwrites it. This makes that safety a property of the code, not of the
deployment — expose the instance directly, or put a header-passing proxy in
front, and it would have been a live hole.
Also COOP: Cross-Origin-Opener-Policy: same-origin on every response, isolating
the browsing context. verdande scripts no other window, so there is nothing to
lose and a class of cross-window attacks to close.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
To headere, appen ikke satte, og som begge følger af, hvad den allerede er.
Sessionen bor i en __Host-cookie, der kun findes over HTTPS — hele modellen
forudsætter TLS. Uden HSTS holder den forudsætning ikke mod en netværksangriber:
den allerførste navigation kan strippes til http://, og cookien rækkes over i
klartekst, før Secure-flaget nogensinde kommer i spil. HSTS lukker vinduet, og
den er sat på nøjagtig samme betingelse som cookiens Secure-flag (secureCookies),
så en dev-instans på ren HTTP aldrig bliver bedt om et certifikat, den ikke har.
To år, underdomæner med; ingen preload — at blive hard-kodet ind i browsere er en
beslutning for domænets ejer, ikke for en selv-hostet app.
verdande beder aldrig om kamera, mikrofon eller placering, så den sikreste
Permissions-Policy er at slå dem alle fra: et indsat element kan ikke bede om det,
siden selv har afvist. Navngivet felt for felt frem for med et jokertegn, fordi
jokertegns-formen ikke forstås ens af alle browsere, og en regel, en browser
ignorerer, er ingen regel.
Prøve på begge: HSTS følger HTTPS og udebliver over HTTP, og Permissions-Policy
lukker for kameraet uanset skema.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Every label link in the sidebar was dead. The route file landed in
web/web/src/routes/ because the shell that created it was already inside
web/ — SvelteKit never saw it, so /etiket/<name> fell through to the
app shell and rendered nothing.
The manifest also listed icon-192.png and icon-512.png, and app.html an
apple-touch-icon, none of which were ever generated. A manifest pointing
at missing icons is worse than one listing only what exists, so the dead
references are gone and the SVG — which Chrome and Firefox install from
happily — is what remains.
docs: hand over the project
HANDOFF.md covers what cannot be read out of the code: why the name is
not skuld, the decisions that look strange until you know the reason,
what is tested against a real service and what is only tested against
its specification, the gaps in the order I would take them, and the
traps that cost the most time to find.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The landing page and README now show the app rather than describing it.
The images are captured by tools/shots, which drives a headless Chrome
over the DevTools protocol — Chrome's own --screenshot flag cannot set a
session cookie, so it would only ever photograph the sign-in page. Kept
in the repository so they can be regenerated when the interface changes,
rather than being something somebody did once by hand.
The quick-add example on the site is in English, with the Danish
equivalent shown underneath — the page is read by people who do not
speak Danish, and the point being made is that both work.
Yggdrasil is stated up front rather than left to the footer: being a
Rune is what this was built for, and somebody running the panel should
learn that in the first paragraph instead of the last line.
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>
actions/setup-python's pip cache needs a requirements.txt or
pyproject.toml to hash, and failed the whole job without one. Putting
the pin in a file rather than inline also puts it somewhere a person
would look for it.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Material for MkDocs under docs/, covering self-hosting, the Rune, the
quick-add and filter languages, importing from Todoist, CalDAV,
mail-to-task, MCP, the AI layer and the API. The version is pinned: the
maintainers have announced that MkDocs 2.0 removes the plugin system
with no migration path, and an unpinned install would break this build
on the day it lands.
The landing page shows the quick-add parser as actual text rather than a
screenshot of it — that is the thing worth showing, and it reads better
as the real thing. It shares the app's design tokens, so the site and
what it describes look like one project.
MIT licence, contributing guide, security policy and issue templates.
Pages deployment is behind workflow_dispatch, so the docs build on every
push but nothing is published until the owner chooses to.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The MCP server speaks JSON-RPC over Streamable HTTP with the six tools
the brief names, authenticated by a personal API token — so a connector
reaches exactly what its owner reaches and there is no second identity
to reason about. A failed tool call returns a tool error, not a protocol
error: a model can recover from the first and can do nothing with the
second.
CalDAV serves VTODO, two-way, so Apple Reminders and Thunderbird can
read, create and complete tasks. Clients authenticate with Basic using
an API token as the password, never the account password — a client
stores what it is given, and what it is given should not be able to sign
in to the app. Completed tasks stay in the collection: a client that
stops seeing one treats it as deleted and drops its own record of having
done it.
The AI layer is one interface with adapters for Anthropic, OpenAI,
Google and any OpenAI-compatible endpoint. That last one is why the
abstraction exists: an integration that only spoke to a hosted API would
be useless to somebody running their own models. Every feature degrades
to "off" when nothing is configured, and the stored API key is never
returned to the settings page.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Comments and attachments close out phase 2. Files are stored
content-addressed by hash, so the path never contains anything the
uploader chose — a filename is attacker-controlled text, and building a
path from it is how "../" becomes a write outside the data directory.
Everything downloads as application/octet-stream: an uploaded SVG served
inline would run its own script on this origin with the session cookie
attached.
Web Push is written directly against RFC 8030/8291/8292 rather than
pulled in — it is three specs' worth of well-defined crypto and about
two hundred lines, and the alternatives carry a JWT and crypto stack
each larger than the file.
Phase 4 imports Todoist's CSV and exports it back. Todoist numbers
priorities the opposite way to how it displays them — its 4 is P1 — so
the two are converted rather than copied; getting it backwards silently
inverts the urgency of every imported task. Nesting is positional, so
the reader keeps an indent stack and the writer never sorts.
The round trip is tested as the brief asks: a CSV in, out, and back
produces an identical project, and two exports of one project are
byte-identical.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The board is one column per section with native drag-and-drop, which
works with a trackpad, a mouse and a screen reader without any of them
being reimplemented. Dropping is optimistic: a card that snaps back for
200ms reads as a failed drop.
Weeks in the calendar start on Monday. That is ISO 8601 and what every
Danish calendar does; a Sunday-first grid makes a Dane misread the month
at a glance. On a phone the chips give way to coloured bars — at that
width the month's shape is the useful part, not the titles.
Label pages run the filter language rather than a bespoke endpoint, so a
label page and a saved filter can never disagree about what a label
selects.
fix(recurrence): "hver mandag", not "hver uge mandag"
A weekly rule that names its days does not also need the word for the
interval. That is how the phrase is said, and it is what the parser
accepts back — the round trip through Describe now holds for weekday
rules too.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Reminders are absolute or relative ("10 minutes before"). A relative one
is resolved against the task in SQL, so moving a task moves its reminders
too. They are marked sent before delivery, not after: a reminder that
goes out unrecorded repeats every minute forever, which is worse than
one recorded that fails to send.
The calendar feed is a per-user token in the path, because Apple Calendar
and Google fetch with no credentials and no way to prompt for any. Tasks
go out as VTODO — the same component CalDAV will serve — and timed ones
also as VEVENT, since Google ignores VTODO entirely.
Templates store relative day offsets rather than dates, which is what
makes them reusable: an onboarding checklist is "day 1, day 3, day 14",
not three dates in March. Building a project from one is a single
transaction, so a failure cannot leave half a checklist.
Backups use SQLite's VACUUM INTO, not a file copy — a copy of a live
WAL database can miss recent writes or catch a page mid-update, and the
result looks like a database right up until it is needed. Rotation keeps
fourteen by count, not by age: a container that was off for a month must
not come back and delete every backup it has.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
"today & p1", "#Firma & @regnskab", "overdue | (today & assigned to: me)".
The grammar is Todoist's, so the import path from it does not require
relearning anything, and both languages' keywords are accepted.
It compiles to parameterised SQL rather than filtering in Go: one
indexed query instead of ten thousand rows crossing the boundary. No
typed text is ever concatenated into the statement — this is a language
people write by hand, which makes it exactly where string-building would
become an injection.
An expression is compiled before it is saved. A filter that cannot run
is worse than none: it is discovered later, as a list that is empty for
a reason nobody can see.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
"vand planterne hver mandag" becomes FREQ=WEEKLY;BYDAY=MO. The stored
form is RFC 5545, not a private format, so the same field will drive the
CalDAV server and the ICS feed without a translation layer.
Ticking off a repeating task advances it instead of closing it, keeping
the same row — so its sub-tasks and comments stay attached. A weekly
review is one thing that recurs, not fifty-two things. The clock time
survives the move, and the completion is still written to the activity
log, because "what did I get done this week" has to include the chores
that repeat.
Recurrence is parsed before dates, and that ordering is load-bearing:
"hver mandag" contains a weekday, so a date parser reading it first
would claim Monday as a one-off and strand "hver" in the title. It is
also resolved before the time-only case, or "hver mandag kl 9" typed
after nine would land tomorrow morning instead of on Monday.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
CI runs in UTC and the API resolves due dates in the user's timezone,
which defaults to Europe/Copenhagen. For two hours out of every
twenty-four those disagree, so tests written against time.Now() passed
all day locally and failed on a late-evening push.
The application was right; the tests were asking it the wrong question.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The interface for phase 1: sign-in and first-run setup, Today, Upcoming,
project views, sharing, Cmd+K search and the keyboard shortcuts.
Quick add highlights what the parser understood underneath the text as
you type — a mirrored layer behind a transparent input, sliced by byte
offset because the server counts bytes and JavaScript counts UTF-16
units, which disagree on exactly the Danish letters this app is full of.
Every local action is optimistic and reconciled afterwards: ticking a
task off strikes it through and animates it out before the request
leaves, and rolls back with a message if the server disagrees.
The Content-Security-Policy is computed at startup by hashing the inline
scripts in the built index.html. Both of them change on every frontend
build, so a hard-coded hash would go stale silently and show up only as
a blank page in production. The alternative, 'unsafe-inline', would drop
the one protection that makes an injected script in a task title inert.
Today is derived from the store by date rather than from the ids that
came back with the first request — filtering against a captured list
meant a task added through quick add never appeared until a reload.
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>
git does not track empty directories, so COPY web/ ./ failed on a clean
checkout with "/web: not found" — the Dockerfile built locally, where
the directory exists, and only in CI.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The HTTP server serves /healthz, the API namespace and the PWA, with the
frontend embedded behind a build tag so a clean checkout compiles without
a Node toolchain. /healthz reads the database rather than just answering:
a process that cannot reach its own data is not healthy, and a 200 there
would keep a broken container in rotation.
The image is distroless and static — the SQLite driver is pure Go, so
CGO stays off. The Rune manifest uses keep_entrypoint because there is
no shell in the image to run a startup command with, and its log watchers
match the JSON log format the container actually emits.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Password hashes are self-describing PHC strings, so the cost parameters
can be raised later without locking anyone out: NeedsRehash reports which
hashes to upgrade at the next login, when the plaintext is briefly at hand.
Session, invite, reset and API tokens are stored only as SHA-256 hashes;
the plaintext exists once, in the link or the reply. Unsalted is correct
here and only here — the input is 256 bits of randomness that has to be
found by value in a WHERE clause.
feat(store): project roles with viewer/editor/owner and explicit denial
Roles are strictly ordered so every check is "at least X". Access to a
task is access to its project: being the assignee or the author confers
nothing, or removing someone from a project would leave them holding
tasks inside it. Checks take a Querier so they can run in the same
transaction as the write they guard.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Parses date, time, priority, project and labels out of one typed line,
e.g. "betal moms i morgen kl 10 p1 #Firma @regnskab".
Both languages are read at once rather than behind a locale switch,
because people mix them mid-sentence. Locale settles only one genuine
ambiguity: a bare hour after English "at".
Each stage reads a copy of the line with earlier matches blanked out,
so no two readings can claim the same characters — without it "kl 10.12"
is a time and, to the date parser, also the 10th of December. Matches
are returned as byte spans so the input box can highlight what it
understood as you type.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Initial data model for verdande: users, sessions, invites, projects,
sections, tasks, labels, reminders, comments, attachments, activity
and filters, plus personal API tokens.
Search indexes a generated `fold` column alongside the original text.
FTS5's remove_diacritics does not touch ø and æ — Unicode treats them
as letters rather than accented forms — so without it a Danish user
cannot find "grøn" by typing "gron". MatchExpr quotes every term so
free text containing FTS5 operators cannot reach the query planner as
syntax.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
