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>
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>
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>
