The update card silently left out the tags and the pros and cons it was
about to write, so the user approved a change the card did not show. An
entry now shows its first tags and how its verdict leans, and an update
names the tags, each side of the verdict and the coordinates it changes.
A new order of the entries is drawn as the entries that move, in their new
places. A changed entry is written back from what the tool answered it
replaced, and a reorder is taken back to the order before, each while
nothing changed since. A Dawarich stay taken in as an entry gets the
entry card; it has no way back, since deleting the entry would leave the
stay marked as taken in.
update_journey_entry now answers previous, the entry's earlier values of
exactly the fields it names (a suggestion written up goes back to being
one), and reorder_journey_entries answers previous_order, the ids in the
order they stood in before. Both come from the service the REST routes
use, which now builds an entry's patch in one pure helper; the routes'
bodies are unchanged. The tools' inline zod moves into strict schemas in
@trek/shared.
Starting a journal, changing its settings, linking or unlinking a trip,
bringing back its suggestions, the user's own view of it and deleting it
fell back to the generic card, which names ids and offers no way back.
They now share a journeyHeader card: the journal with its trips, the one
the change links or unlinks marked, what a new journal brings in and what
a deletion or an unlink takes, and each setting old to new in the
journal's own words. A new journal is deleted again while nothing was
written, added or laid out in it, changed settings are written back from
what the tool answered, a linked trip is unlinked by its owner while none
of its suggestions was written up, and the own switch flips back.
The MCP tool lacked show_trip_tracks and cover_gradient, which PATCH
/api/journeys/:id has always taken. Both now read the input through one
helper, and the tool goes through a small settings service that writes the
same patch in a transaction with the stored values it replaces, answered
as previous, so a change can be written back. The subtitle and the cover
gradient take null to clear them. The tool's inline zod moves into strict
schemas in @trek/shared; the REST route and its body are unchanged.
Asked on /journey to create "Japan 2026", the home chat had nothing to
offer: it keeps no write that names a trip or a journey. It now keeps
create_journey, whose trips the tool checks one by one, and delete_journey,
which the journey's own chat leaves out because the conversation goes
with it. For anything inside a journal it offers open_journey_chat, the
twin of open_trip_chat: the journal is read from the user's own journals
and shown as a card whose button goes on in the journal's chat with the
question waiting there. The trip and journal cards share their question
and button.
Asked on a journey page to write an entry, the assistant said it could not:
the only journey chat was the Studio's, which keeps the journey's writes
out. A journey session now holds what either page offers and shows the
model only the asking page's tools. The journal page offers a viewer the
reads, an editor the entry, photo, recorded day and day import writes, and
the owner also the journey's own settings and trips; delete_journey stays
out of the journey's own chat. A few reads that name no journey come along
(place search, the photo libraries, Dawarich stays), the Dawarich journal
entry is pinned through its journalId, and an entry an argument names must
belong to the conversation's journey before the tool runs. The turn reads a
journal card and instructions of its own; the Studio keeps exactly what it
offered before.
The journey's assistant lives in TREK Studio today, and the journal page is
about to get one of its own over the same threads. The chat and decision
bodies take an optional surface, studio or journal, and the journey scope
carries it to the service; left out it reads as the Studio, so today's
client is unchanged. The scope key ignores it, so both pages keep one
thread list per journey.
lint:test-sql counts every .prepare( under tests/ as a raw statement, and the
attachments service's prepare() was called five times in its unit test. The
test holds no SQL; the method takes a name that does not read as one.
The server built the answer through words.text(), words.count() and maps of
plain strings, so the check read all 13 assistant.attach keys as unused. The
helper's lookup is t() now (a numeric count picks the plural form, as the
client's does) and the chip and reason maps hold their keys under *Key
properties.
The chips offered to keep an attached file in Files, but nothing could do it:
the assistant's upload_trip_file stays denied, and the file never reached
Files. A new server write, keep_attached_file, is offered to the model where
the thread holds an attachment and held as a change card naming the file and
the booking, expense or place it goes with.
Applied, it runs the checks of a Files upload with the user's rights (the
demo block, the trip, file_upload and file_edit for a link, the instance's
file types, every linked id on the same trip), copies the bytes to a trip
file of their own, and writes the trip file, its expense link and the
attachment's pointer to it in one transaction; the members' planners get
file:created after it. A second keep of the same attachment answers the file
kept the first time. FilesService gains storeBytes and discardBytes so the
storage write stays out of that transaction.
The receipt opens the Files tab; the card's verb, its "Attached to" row and
the receipt's open label are new keys in all 27 locales. Undo is not offered:
no tool takes a trip file back yet.
The assistant could not read a file the user attached: the bytes were gone
after the request, the thread only held the file's name, and read_trip_file
stays denied because it would send any document of the trip to the provider.
A new server tool, read_attached_file, reads only the files attached in this
conversation by this user; any other id is answered "No such attachment in
this conversation.", whoever it belongs to. It is offered in a trip turn whose
thread holds a file with text. The first read of a file is held as a change
card that names the file and the model and host its text would go to; once
the user agrees, the agreement is kept on the attachment and later reads run
at once. The text reaches the model through the history and, for a later
read, as a tool answer only the model gets (AgentToolRun.modelText): no message
part, stream chunk, shared answer or client store ever carries it.
The model is told each kept file's attachment id, and the standing
instructions say to read the file when the user wants to work with it, to
propose a booking found in it through create_reservation and then to offer
keeping the file with it. The card's verb, its "Sent to" row and the step's
name are new keys in all 27 locales.
A booking file without a booking ended the answer on the error "No booking
found in this file." with no action, and the user was left to type. Now the
server answers every booking file itself, without a model: one line that
names the file and what TREK found in it, or that it found nothing, why, and
asks what to do with the file. Under it come up to three chips, picked from
what the user may do on the trip and what the file allows: keep it in Files,
make a booking from its text, attach it to a booking or an expense, ask what
is in it, or keep it with the booking just found. A chip sends its words as
an ordinary chat message.
The line and the chips are written in the language of the request from new
assistant.attach.* keys in all 27 locales, through a small helper the sports
proposals now share. The empty answer finishes as stop; no_bookings_found
stays in the contract for the threads older builds wrote. Route files keep
their answer as it was.
The chat's booking reader kept only the bookings of the import preview and
dropped its warnings, so "AI reading is not set up", "the AI failed",
"a scan without text" and "nothing in it" all came out as the same
no_bookings_found. The reader now reads the reason from the preview (the mode
it ran in and the AI fallback's warnings) and keeps it in the stored read
step, and the note the model is sent names it.
A file attached in the trip chat lived only as a buffer for the one request
that read it, so the assistant could not look at it again and nothing could
keep it in Files. Now its bytes go to storage before the turn writes anything
(under the trip files' category, which is never served by path) and a row in
the new assistant_attachments table keeps its name, type, size, hash and the
text TREK read out of it, written in the turn's opening transaction. The
message's attachment part carries the row's id; old messages without one still
read.
The text is read the way the AI import reads it, through a new public
LlmParseService.readText, and a file whose text cannot be read is kept all the
same. A storage that refuses the bytes refuses the turn before any row exists.
Deleting a thread takes its files along, and the nightly retention sweep drops
files older than seven days and bytes no row names any more.
The rhythm test holds the picker to what it does now: it gives the rhythm up
only where no template of the book's styles frames every photo and keeps it.
A design applied over a stored book keeps that book's theme, as the merge has
always done, so the end to end test checks the pages instead. The MCP test
builds its request through the shared schema, a travel mark's frame is read
with its sides spelled out for the client's looser types, and the client's
react-hooks/refs baseline drops to the 555 it holds now.
The design_book tool says in one sentence that layouts: 'templates' lays
every page on the Studio's designed templates in the archetype of the
book's theme, as the Studio's Auto layout does, and that each plan row then
names its template; style classic alone stays the old built-in Auto
layout. The field comes from the directives contract in @trek/shared, so
the tool's schema takes it without a zod line of its own, and the answer's
plan row gains an optional template. The REST draft routes take no
directives, so nothing changes there. Without the field the answer is the
same as before, no row naming a template.
Every style now has four covers and five double spreads, 108 in all, and the
spreads of each style take different photo counts, from a words-only page to
eight photos, so a book can be laid on them without an empty frame. The five
new styles come with their own themes: Riso (overprinted spot inks), Magazine
(a travel magazine), Retro travel (vintage posters), Midnight (a dark film
look) and Field notes (a traveller's notebook). Each new style has a cover
composer for the design engine and a recipe for the assistant, and its chip,
theme and template names are translated into every language.
The card that opened claude.ai's custom connector dialog for this instance
goes, with its phone twin, the line in the assistant setup that jumped to it,
its endpoint and its contract. Anyone who wants Claude uses TREK's MCP
server under Integrations, or an Anthropic key in the assistant. It came with
the assistant and never shipped in a release.
The calendar offers only the plan's years, but a vacation day or company
holiday could be written for any date. A day set months ahead, as the
assistant did for 6 January 2027, was stored and counted yet never shown,
because 2027 was not a year of the plan. Writing a day now adds its year,
with every member's allowance, the way opening it by hand does; the year
is the writer's leave period that holds the date. This holds for the app,
MCP, plugins and the assistant alike, since they all write through here.
The index holds a mountain as many pins named by whoever listed it, at its
foot as much as on top, so a hike up Mt. Takao listed it five times under
names like Mt.Takao, 東京都 高尾山 and 高尾山 (Mt. Takao). Rows that are one
place now merge as a group: like names in one spot for every kind, and for a
summit of the index like names anywhere on the mountain, linked through a
name that carries both scripts. The row kept is an OpenStreetMap object over
an index pin, then the plainest name. Two OpenStreetMap summits stay two.
Removing a member deleted their membership row only, and the invite link
checked nothing but its own token, so whoever kept the link walked straight
back in (GHSA-wr4c-964p-39jg).
trip_member_removals now notes who another member took off a trip. The invite
link refuses them on preview and on accept with a 403 that says so, old link
or regenerated, and the join page shows that instead of the join button.
Adding them back by name, or through a trip-bound invite or a plugin acting
for a member manager, lifts the note. Leaving a trip yourself leaves none, so
the link keeps working for whoever left and for everybody else.
restore_book_layout took any layout the caller sent, so a layout naming a
photo of another journey was kept, and laying a page out on it put that photo
into this book while place_photo refused the same id. The layout is now held
to the rule a page restore states: every photo it names, in a frame, on a map
marker or in the letters of a text, is in the gallery or on a page of the book
already, or the call is refused with photo_not_in_gallery.
restore_book_page and the design apply read the photos of a page in one place
now (book-photo-refs.ts), which counts the photo a text is filled with. A page
put back with letters filled with a photo from outside the gallery is refused
as a frame of it would be, and a designed page whose letter fill photo left
the gallery since is skipped as photo_gone; on a new book's cover the letters
keep their colour instead, as its frame is emptied.
A saved layout keeps no photo of the page it was taken from in its letters, as
it keeps none in its frames, so laying another page out on it no longer
carries that photo along. A layout kept before this fills such letters with
the first photo of the page it is laid on, or leaves them in their colour.
The style operation checks a letter fill photo only when the change sets the
fill, so a title whose photo left the gallery can still be resized or
recoloured, as the text operation already allowed.
The search behind propose_hike_leg_way is kept for a while under the spots of
the hike, but it kept the finished points of the first call. A later call over
the same spots in another form, such as a round trip given with its way back as
its last point, or with other names or stage ends, got the first call's points
back, and its create_with no longer came back to the start. The search now keeps
only the pins that hold each way, and each call sets them on its own points.
A new point within 25 m of a saved one took that point's key, name and place
link, even when another new point already stood on it. A stop put in just
before a stop a stage starts at took the stage's key, so the stage left its
day and the undo could not bring it back. The saved points are now matched one
to one, the nearest pairs first, so a point standing on a saved one keeps it.
The points a hike is changed through carry no shaping mark, so an inserted or
removed stop and a reshape turned every shaping point into a stop. A via point
standing on a saved shaping point now shapes the line still, unless a stage
ends there.
A GPX import keeps no points of its own, and the tour read makes up a start
and an end from its line. update_tour with reshape turned or closed those two
made up points, so the recorded line was replaced by a router line between its
ends. A reshape of a tour without points of its own is now refused with the
recorded track wording, before anything is planned or saved.
The home chat kept every write whose arguments named no trip and no journey,
so the journey group brought update_journey_entry, delete_journey_entry and
reorder_journey_entry_photos (they name only the entry) and the Dawarich
journal entry (it names the journey as journalId). The writes of the
journey's controllers now stay out by their controller, and journalId counts
as a journey, as the home chat's own contract and prompt say.
The open changes of a thread are now the ones still inside their decision
window. A call older than a day already reads as expired in the thread and
can no longer be decided, but it stayed approval_requested until the nightly
sweep, so "+ Tour", "+ Day" and "Plan this" answered decide_first with
nothing left to decide, and a decision had to name the expired call too.
listOpen takes the window's start, and every caller passes the same cutoff.
- design_book takes a brief (energy, decoration, collages, theme), a cover
archetype and a cover lockup, and pages.overrides that give single pages of
the plan another beat or layout. Directives written before parse as they
did, and a design asked for none of it is composed exactly as before.
- The engine composes the seven cover archetypes from the book's own photos,
words, theme faces and colours, lockups, shapes and stickers, varied by the
seed: spine band, poster pop, cut-out, illustrated postcard, grid and
badge, minimal serif and stamp collage. A title the directives give a
display tier is held to it, and the notes say when a band, a badge or a
stamp holds it smaller or a cover leaves a layout out.
- A lively or loud book turns two in five hero and grid spreads into
collages, script overlays, badge grids, stamp rows or two-tone splits, the
first of them always, turns and frames the prints of its other pages, sets
its cover title larger and takes one or two, or three to six, stickers of
its theme's motifs a spread, never over words, a photo's detail or the
fold. A calm book asked for collages gets them and nothing else.
- Every turn the engine gives a print or a sticker stays within what the
brief's energy takes, a calm book's within its theme's own, so a design is
never judged against its own brief.
- New checks name a flat cover, a page without a lead, colours or faces off
the theme and, for a design made with a brief, a book livelier or calmer
than it asked, on the pages the design made and on a page revised in the
draft. Page edits answer with the art checks too, and the assistant's
cards name them in every language.
- list_book_assets lists the shapes, faces, lockups, themes and patterns
beside the stickers, and the Studio's shape groups and photo frames are one
list the assistant reads too.
- The Studio prompt gains an index of themes, archetypes and faces and JSON
recipes of the elements to add and style for each cover and three lively
spreads, and a turn that designs the book may preview sixteen pages, still
three images a request; a viewer is told of none of it.
A decorated template is a whole designed page kept as data: full document
elements in fractions of the page they were drawn on, with roles for the
photos and words a page brings, links to the theme for its colours and
faces, groups for its lockups (a title with its date line, a badge with its
words, a stamp with its postmark) and an archetype with tags. Seven cover
archetypes in three variants each and sixteen double spreads ship in
shared/src/book/templates/data.
Laying a page out on one pours its photos into the photo roles in order and
its words into the title, subtitle, date, story and caption roles, takes
the words it has none for from the book or the journal entry, sets the
template in the book theme, scales it to the page format with its bleeds
on the bleed of that page, and parks what has no room, a date line the date
mark was not made of included. A text set on a colour is made to read there
at the size it was fitted to, on a band of ink or paper when neither reads.
A mark set as text, such as a large quotation mark, is design to every
layout and never taken for the words of a page.
A fitted text keeps the size it was drawn at as its ceiling, so a shorter
title grows back, and every fitted text is now solved with eight percent of
headroom on letter width: set in the browser, the bold condensed faces and
several scripts run that much wider than the letter measure, and a fit at
exactly the measure wrapped its last word out of the frame.
The layout operation of edit_book_page and revise_book_design takes the new
ids as a checked string and keeps the name of a locked group,
list_book_layouts lists them with archetype, tags and roles, and the design
prompt names them. A sibling extract script reads a page drawn in the
Studio back into the format, roles, tints and groups kept.
- The element, spread, document, page operation and card unions carry a
name of their own, so the declarations of every schema that holds them
refer to them instead of spelling them out again. The shared declarations
shrink from 9 to 5.5 MB and the server's typecheck from 4.4 to 2.9 GB, so
the build fits the image's 4 GB again.
- edit_book_page and revise_book_design take add by what the element is,
with an id of its own; its look follows with style by that id in the same
call, every look field described once. A change an assistant card kept
with its look on add still reads and runs.
- restore_book_page states what every element has once, then each kind's
own fields and the type the five travel kinds share, without defaults; the
page is read as a spread again before it goes back.
- The theme links are explained once in the page edit's description, and
style points a text's face, a shape's paint and outline and a photo's crop
look at their one full description.
- The lockup roles live in a module of their own, so the operation schemas
no longer import the lockup engine, whose cycle left the operations unset
in the shared tests.
- The theme switches no longer fall through a comment, the newer document
test follows the current revision, the line inspector names its stroke
keys, a text's anchor reads no physical side, two shapes record the
proportions they are drawn at, and the photo look and line tests follow
the slider and the folded ornaments.
A GPX file that mixes routes and tracks gives each its own text: the pieces
are matched to the reader's rows by kind, routes first as the reader gives
them, where they were paired by index and a route got a track's points. The
place pictures reach the network through a small repo instead of the api
module, the wanderer parity case and the tool catalog test allow wanderer,
and the knip and theme baselines follow the lower counts.
The output items of a step were replayed as they came, web search calls
included. With store false the provider cannot resolve such a call again and
refused the next step with HTTP 400, which ended the turn with an error right
after a hike was proposed. The search calls are left out of the replay; what
they found is in the answer's text and its sources.
A third scope, home, next to trip and journey: threads that name neither a
trip nor a journey (the CHECK now only forbids both), reached under
/api/assistant by their owner only. A home turn reads the user's trips
through list_trips into a short card (under way, next, later, behind,
undated), offers every read (a trip's on the id the model names, checked by
the tool with the user's rights) and only the writes that take no trip or
journey (atlas, vacation planner, collections, tour library, settings), all
held as change cards. open_trip_chat answers with a card that goes on in
that trip's own chat with the question waiting in its composer.
On the desktop the window opens on the home chat outside a trip; its head
lists the trips to switch into and a switched trip chat has the way back.
On the phone the home chat opens full screen from the dashboard head and the
dock's More list, and the card opens the trip with its chat. Both run on
useAssistantHome.
P6: insert_tour_stop and remove_tour_stop take a place into a saved hike or
city walk as one stop and out again, each the other's undo, with change
cards in the chat. The planner's insertion rule (poiInsertion) moved to
shared so the planner and the server place a stop the same way. "+ Tour" on
a found place holds it as a stop of the saved tour open in the planner.
P7: GPX, KML and KMZ files attached in the chat are read into their tracks
and each is held as a change that takes it in as a hike through
import_tour_gpx, undoable per track; the GPX text stays on the held call.
The assistant can now search a round hike of about a wished length from one
point and the router's other ways for one leg of a hike, with the planner's
own search, and propose each one as a hike card to compare and take. It can
also search the user's wanderer trails, preview one as a card, import it and
check a wanderer tour against its source.
The round search, its loop geometry, the test whether two lines are one way,
the other ways among a router's offers and the pins that hold a chosen way
move to @trek/shared; the planner and the road trip use them from there.
City walk changes take edit, reverse and close_loop; edits alone keep the
saved way and never ask the router. update_tour turns a hike round or closes
its loop with reshape. New MCP tools mirror the Tours tab's REST writes and
reads: update_tour_details, set_tour_route_color, copy_tour,
classify_ski_track, set_paddle_plan, decide_paddle_obstacles,
restore_recorded_track, get_tour_trail_details and find_horse_routes, with
change cards, undo where the answer keeps the values before, and broadcast
parity cases.
The ids of long catalogues (fonts, shapes, patterns) read as a checked string
in the book tools' schemas, so restore_book_page and the page edit stay under
their ceilings. The lightbox takes its reading direction from the language.
Baselines follow the removed avatar upload and the lower counts, the doubled
NEWER constants and three unused imports go, the locale indexes are sorted,
and the place gallery, picture, sheet, inspector weight and paddle tests
follow the merged behaviour.
Elements can be grouped on a page and picked, moved, resized, aligned and
restacked as one. A layers panel lists the page front to back with lock,
visibility, rename and drag to restack. The sheet gains marquee selection,
arrow-key nudge, one box that resizes a multi-selection with Shift holding
the proportions, and the design-tool shortcuts. The inspector lines a
selection up and spaces it out, and copies and pastes a style.
The assistant gets the same through the group, ungroup, name and hide
operations, and describe_book_page lists the groups. The format gains the
optional group, name and hidden fields and a spread's group names, so
BOOK_SCHEMA_REV goes to 2.
A new element kind, sticker, draws layered vector illustrations from a library in twelve themes, behind its own entry point @trek/shared/stickers. Studio gets a Stickers rail section (themes, localized search, recently used, click or drag to place) and an inspector for colour slots, mirroring, turning and opacity. The assistant gets list_book_assets, add and style of stickers in edit_book_page, stickers in describe_book_page and an overlap warning for a sticker over words. BOOK_SCHEMA_REV goes to 2.
The book catalogue grows from 7 families to 34, all self-hosted through
@fontsource under the SIL OFL 1.1 or the Apache License 2.0: condensed and
poster faces, heavy retro display, elegant display serifs, Montserrat, twelve
scripts and DM Mono. Weights run from 100 to 900, each family offering only
the weights it ships, and the serifs gain real italics.
The catalogue lives in @trek/shared (book-fonts.data.ts) with each family's
roles (display, heading, body, script, mono), weights, italics and letter
width, so the Studio, the findings, the design engine and the assistant read
one list. Page operations and the design engine set a weight a family lacks
at its nearest one, describe_book_page names the role and the weight, and
font_mix no longer counts scripts and mono faces, warning above three.
The Studio gets StudioFontPicker: the current family set in itself, a
searchable list grouped by kind with every family in its own face and the
book's own families first, and a weight slider over the weights the family
has. Faces load only when used; the assistant's page snapshot embeds only the
faces a page draws, the service worker installs only the latin files of the
original seven families, and the faces of an opened book are cached for
offline use. BOOK_SCHEMA_REV goes to 2.
The registry refuses a package with more than two prompt lines at load, which
failed every suite that boots the assistant. The planning line now holds the
tools, the profiles and the hike rules.
The assistant can now plan and save every type the Tours tab plans. A bike
tour or a run is proposed and created through the hike's own plan and save
(propose_tour, create_tour), routed on the server with the costing of its
profile, now kept once in shared and read by the planner as well. A paddle
or ski tour planned with plan_paddle_route or plan_ski_route is saved with
create_paddle_tour or create_ski_tour, and "Plan this" takes those plans,
bike tours and runs too. Every create has its card and its way back.
- Web search: ChatGPT (Responses web_search), Anthropic (web_search server
tool) and OpenRouter (web plugin) search the web themselves when the admin
switch allows it (on as it ships). A search shows as a step ("Searching the
web for ..."), the cited pages as source chips under the answer. Anthropic
answers that searched are replayed with their blocks (new provider state
adapter); the search step never goes back to the model as a call. The
prompt says when to search and that chosen places still go through
search_place.
- Tour writes: assign_tour_track (undo: take that assignment off),
unassign_tour_track, set_tour_activity_excluded (undo: the other switch),
link_tour_packing and unlink_tour_packing (undo from the link before, which
both answers now name) get change cards and their ways back.
Maurice