`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>
`assignee_id` has been on tasks since sharing was built and delegating has
been possible from the drawer since yesterday. What was missing was
anywhere to see it: work handed to somebody else left your lists and
appeared in nothing.
GET /delegated returns everything assigned to somebody who is not you, in
the projects you can see, grouped by the person. Grouped on the server
rather than flat, because the question is about people — "what is Anders
sitting on" — and a client cannot group it itself: it would need the name
behind an assignee id from a project it does not happen to have open, and
there is no way to ask for that. The names come back with the tasks, so
one request is one screen.
The filter is a field of its own rather than a sentinel in AssigneeID.
"What is on my plate" and "what have I handed over" are different
questions, and one string that means an id most of the time and a magic
word the rest is a field somebody eventually passes a real id to.
An assignee whose account is gone is named "Ukendt" rather than dropped.
Losing the row would make work disappear from the one view that exists to
stop work disappearing.
The sidebar entry only appears where delegating is possible at all. On an
instance with one person it could never have anything in it, and a
permanent empty entry is a question the sidebar keeps asking and answering
"no".
Building it turned up a bug in the split above it. "Projekter" and "Delt
med mig" were divided on `shared`, which only means the project has more
than one member — so inviting somebody to a project of your own moved it
under "Delt med mig", where it lost its place in the order, stopped being
draggable, and could not be filed under a group. It is divided on
ownership now, which is what the two headings have always said. Sharing
your own project is not the same event as somebody sharing theirs with
you.
The smoke test now follows the whole loop in one go: invite, accept in a
second browser, assign a task to the person who just joined, and find it
under their name — with the shared project still under "Projekter" on the
way past.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The three the handoff named as next. They are one commit because they are
one mechanism: all three end in something being dragged, and a drop target
cannot tell what is coming without the module they now share.
Groups are foldable headings over the projects in the sidebar. A table
rather than a `group_name` column on the project, because a group has to
be renamable in one write, has to survive being emptied, and has to
remember whether it is folded — none of which a string repeated on every
project row can do.
Folded state lives on the row, not in localStorage. The sidebar's *width*
is a property of the screen you are sitting at, which is why that one is
per browser; a folded group is a statement about the group — "this is the
part of my work I am not in right now" — and it is true on the laptop and
on the desktop. There is nobody else's answer to disagree with either: a
group belongs to exactly one person.
A shared project cannot be filed. `group_id` is a column on the project
row, so a member grouping somebody else's project would move it in the
owner's sidebar too — the same reason `sort_order` is owner-scoped. The
listing reports the column only to the owner, so a viewer is never told
where somebody else keeps it.
Deleting a group takes the heading and leaves the projects, and the
sidebar decides where a project renders by whether its group still
exists rather than by the id alone. A group deleted in another tab
arrives as one event and not one per project, so for a moment the
projects still name a heading that is no longer drawn — filing by the raw
id would drop them out of the sidebar entirely.
Kommende gains the month grid the project pages already had, behind a
Liste/Kalender toggle. The two views ask for different things — seven days
from today against six whole weeks around an arbitrary month — so each
loads its own, and the grid reports which dates it is showing rather than
having the page guess. Which view is remembered in localStorage: a month
of seven columns needs room, and the answer on a phone is not the answer
on a wide monitor.
And a task can now be dropped on a project in the sidebar, on a day in
Kommende, or on a cell in any month grid. Onto a project it is a *move*,
not a field: `sort_order` belongs to the project, so it has to find a
place among that project's tasks and leave its old section behind.
Each drag now carries its own MIME type. `getData` is deliberately
unreadable while a drag is in the air — the browser hands the payload over
on drop and not before, so a page cannot read what is being dragged across
it — and `dataTransfer.types` is all a target has to decide with. Deciding
is the point: calling preventDefault on a drag you cannot accept is what
turns "no" into a silent, wrong drop. The sidebar takes a project and a
task on the same row and has to tell them apart.
Two things fell out of building it. The month grid has always had one cell
narrower than the other six: `.today` styled the "I dag" button in the
header, and the day cell for today wears the same class, so `margin-left:
auto` was shrinking a grid item to its content. It is scoped to the header
now. And a project page listed whatever was in the store rather than what
belonged to that project, which did not matter until a task could leave a
project while you were looking at it.
Covered by eight new API tests and two new smoke tests, and the smoke tests
drive the drags for real — the type check they exercise exists only while
a drag is in flight, so nothing else can reach it.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Search covered task text only, so "regnskab" found nothing with the task
labelled @regnskab sitting in front of you — which reads as the search
box having lost it.
A label is often the only thing you remember. "That thing about the
accounts" is a search for @regnskab, not for any word in the title.
The label side is a plain lowercase match rather than a second FTS index.
Labels are short, and their names are typed by the same person now
searching for them, so there is no spelling to be generous about — the
diacritic folding that earns its keep on task text does not earn a second
index here.
The join sits inside the WHERE the visibility rules already build, so
somebody else's label cannot pull their task into your results. There is
a test for that, because it is the kind of thing an OR is good at
breaking.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Four things you could not do to a task you had open, and one that had
never worked at all.
**Project, recurrence and assignee** are now fields in the drawer. A task
created in the wrong place could only be fixed by dragging it, a repeat
could only be set by typing it into the title when the task was created,
and delegation had no interface whatsoever despite assignee_id being in
the API from the start. The assignee only appears on a project with
somebody else in it, because on your own there is nobody to choose.
**The title is read the way quick add reads it.** Typing "i morgen kl 14
p1" into a title used to leave it as those words, so where you typed a
sentence decided what it meant. The parse runs on the server — the
grammar is Danish and English and lives there — and applies only when it
consumed something. What it took is said out loud, and the fields on
screen are updated to match: the drawer otherwise seeds its inputs once
per task so a save cannot overwrite what you are typing, and that rule
has to bend exactly here, where the save changed the very fields in front
of you.
**And the member list has never worked.** The share panel, and now the
assignee field, ask for it. Every call errored: the ORDER BY named an
expression, and SQLite only accepts result-set columns across a UNION, so
it failed at query time with "1st ORDER BY term does not match any column
in the result set". Found by the smoke test that opens a task, which is
the second real bug that suite has caught by watching for failed requests
rather than only for what renders.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Projects have carried sort_order since the first migration and nothing
ever set it, so the sidebar was ordered by creation date for good.
POST /projects/reorder takes the whole list rather than one move. A
person has a handful of projects, so sending the order you want is
simpler to reason about than midpoints between neighbours — and it cannot
run out of precision, which is the failure the task ordering has to
respace a section to recover from. It also cannot land half-applied the
way a sequence of individual moves can.
Projects you do not own are skipped rather than refused. sort_order is a
column on the project, not a preference per viewer, so a shared project
sits where its owner put it and a member rearranging their own sidebar
does not rearrange somebody else's. The sidebar only makes your own
projects draggable, so that rule never shows up as a row that springs
back.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
A project could be created and shared and never renamed or deleted. Both
have worked through the API since the beginning; there was simply nothing
to click.
The heading is now the field — a heading that happens to be editable
rather than a form that looks like one — and saves on blur, with Escape
putting the old name back. Owner only, and the Inbox keeps its plain
heading because it cannot be either renamed away or deleted.
Deleting needed more than a button. It is soft, with thirty days to
change your mind, and restoring has been possible the whole time — from
an id, which is exactly what you no longer have once the project has gone
from the screen. A recovery window nobody can reach is not one. So
GET /trash/projects lists what you have deleted, with how many tasks went
with it and how long is left, and Settings → Data has the button.
Owned, not shared: a member of a project somebody else deleted has no
business bringing it back, and there is a test that says so.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
docs/api.md has told people to make a token under Settings since it was
written. The store has held CreateAPIToken, ListAPITokens and
DeleteAPIToken since the first migration. There were no routes: nothing
between the two, and no way to make one.
GET, POST and DELETE under /tokens, all behind a new requireSession
middleware. A bearer token is refused there with 403 even though it is
accepted everywhere else — otherwise a leaked token is permanent, because
whoever has it issues a second one and revoking the first changes
nothing. The plaintext comes back from POST and never again; only the
hash is stored, so the interface has to say so at that moment rather than
offering a reveal that cannot work.
PATCH /auth/me alongside it. Name, timezone and language could not be
changed anywhere — not through the API and not through the interface —
and an account created from an invite inherits a default timezone. That
is not cosmetic: every date in the app is resolved in it, so somebody in
another country had every due date land an hour out with no way to say
so. The zone is validated against the running system's database rather
than a list kept here, which is the same database the dates are resolved
with. The email address stays read-only: it identifies the account and is
what invites were sent to.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Two people saving at the same moment got a 500 after two milliseconds.
The DSN has set busy_timeout since the first commit, and it covered none
of the contention it looks like it covers. With a plain BEGIN a write
transaction starts as a reader and asks for the write lock at its first
UPDATE — and SQLite refuses that upgrade with SQLITE_BUSY immediately,
without applying busy_timeout to it. Backing off cannot help: the
transaction is already holding a read snapshot the other writer is
invalidating.
_txlock=immediate takes the lock at BEGIN instead, where the timeout does
apply and the second writer waits its turn. The driver leaves read-only
transactions deferred, so readers still run concurrently, and every one
of the twenty callers of db.Tx is a write.
Found by opening a task and saving a description, a sub-task and a
comment at once — three writes, one of which came back a 500. The test
fails without the flag.
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>
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>
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>
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>
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>
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>
