Commit Graph

1737 Commits

Author SHA1 Message Date
Maurice de497d15a4 test(assistant): the attachments repository on its own, every read, write and sweep step
The repositories are held to 99 percent of their statements, and the new
attachments repository was reached only through its services' mocks.
2026-10-24 22:32:48 +02:00
Maurice 05666295e0 test(assistant): every keep proposal in the attachments e2e takes a call id of its own
The refusal test proposed two keeps in one thread under the same call id, so
the second decision met the first call, already decided, and no refusal came
back. Each proposal now has its own id, and the refused right is set after the
proposal so it is the apply that refuses.
2026-10-24 22:32:48 +02:00
Maurice 62da83f5f7 test(assistant): the keep test reads the createFile call through a typed tuple
The mock's call list types as an empty tuple, so indexing its fourth argument
failed typecheck:tests.
2026-10-24 22:32:48 +02:00
Maurice b333910533 test(assistant): the attachments e2e provider answers the model list a saved connection asks for
Saving the custom connection lists the server's models first, and the fake
provider answered that with a 404, so the setup got 502. It answers /api/tags
the way the other assistant suites' fake provider does.
2026-10-24 22:32:48 +02:00
Maurice 2d1da19152 fix(assistant): the step that keeps an attached file's bytes is called stash
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.
2026-10-24 22:32:48 +02:00
Maurice e7ac46c756 fix(assistant): the keys of the attached-file answer are named where lint:i18n-keys sees them
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.
2026-10-24 22:32:48 +02:00
Maurice f1a2174f96 chore(assistant): the attachment work exports only what other files use
Types that only their own file reads lose their export, so knip's
unused-exports ratchet does not grow with the attachment work.
2026-10-24 22:32:48 +02:00
Maurice 89c33ac3f4 feat(assistant): an attached file can be kept in Files, on its own or with a booking or an expense
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.
2026-10-24 22:32:48 +02:00
Maurice aeda658f18 feat(assistant): the model reads an attached file once the user agrees
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.
2026-10-24 22:32:47 +02:00
Maurice 2f3a0219cd feat(assistant): every attached booking file gets an answer with what to do next
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.
2026-10-24 22:32:47 +02:00
Maurice 41fb5759e2 feat(assistant): an attached file without a booking says why
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.
2026-10-24 22:32:47 +02:00
Maurice 6a77496438 feat(assistant): an attached file stays with its conversation
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.
2026-10-24 22:32:47 +02:00
Maurice 487f8dd886 refactor(assistant): the answer to an attached file is a provider of its own
AssistantService sat three lines under the size limit, and the attachment
work ahead grows exactly this answer. Moving it into AssistantFileAnswers
leaves the rows and their transactions with the service, which hands the
answer the two ways it writes its first row. Nothing the user sees changes.
2026-10-24 22:32:47 +02:00
Maurice 4cc62f4c4e test(journey): the design_book request in the MCP test takes the journey beside the parsed directives 2026-10-24 20:58:49 +02:00
Maurice cb34c46226 fix(studio): CI on the templated auto layout
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.
2026-10-24 20:54:16 +02:00
Maurice 9729b0b575 feat(server): design_book offers the designed templates
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.
2026-10-24 20:13:43 +02:00
Maurice 8ce3b24a01 feat(studio): 71 more designed pages and five new styles, each with a theme of its own
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.
2026-10-24 20:13:41 +02:00
Maurice 728a275fef chore(assistant): drop Connect with Claude from the integration settings
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.
2026-10-24 18:28:41 +02:00
Maurice f6befaa6b2 fix(vacay): the opened year's broadcast skips the socket the change came from, like every other
The app only sets days in the years it shows, so the tab that made the change
never needs the new year; the assistant, MCP and plugins send no socket and
reach everyone.
2026-10-24 18:28:38 +02:00
Maurice fd6d3fddd5 fix(vacay): a year a day opens is announced after the day is committed
Opening the year sent vacay:settings from inside the day's transaction, so
a client could reload the years before they were there. The rows go in
with the day, and the broadcast follows the commit. The helpers file is
formatted the way the server's Prettier wants it.
2026-10-24 18:07:02 +02:00
Maurice 280e55bbc9 test(vacay): a day in a year the plan has not opened also announces the new year
The broadcast parity cases toggle a day in 2027, which the seeded plan does
not hold, so both MCP and REST now send vacay:settings for the opened year
before vacay:update.
2026-10-24 17:31:47 +02:00
Maurice e84060cdf7 refactor(vacay): the pure constants live in the helpers, so the service keeps its size budget
The holiday feeds' limits and patterns and the colour palette move to
vacay.helpers.ts, which holds the vacay domain's pure half already. That
keeps the service under its line budget after the missing-year fix.
2026-10-24 17:31:47 +02:00
Maurice fbc85b05a1 fix(vacay): a day set for a year the plan has not opened adds that year
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.
2026-10-24 17:31:47 +02:00
Maurice 736594696e fix(tours): one summit per mountain in the places along a tour
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.
2026-10-24 13:54:48 +02:00
Maurice d0f74c9f02 feat(studio): add_book_pages, set_book_cover and design_book's cover take the decorated templates too 2026-10-24 11:07:16 +02:00
Maurice 44ea1ea0ba fix(places): search_place asks for one place per query, so the assistant stops bundling four names into one search 2026-10-24 10:07:59 +02:00
Maurice 3bee600096 fix(assistant): a step that searched the web and called a tool no longer sends ChatGPT an answer to the search, which it refused 2026-10-24 10:07:59 +02:00
Maurice e96813edcf fix(places): search_place says what locationBias does, so the assistant passes the neighbourhood instead of the city centre 2026-10-24 10:07:58 +02:00
Maurice 1487ad97f1 test(trips): the removal names who removed 2026-10-24 08:58:56 +02:00
Maurice 658536c217 fix(trips): a member another member removed cannot rejoin through the invite link
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.
2026-10-24 08:29:51 +02:00
Maurice 090e754077 fix(studio): a restore brings in no photo from outside the journey's gallery, letter fills counted
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.
2026-10-24 04:05:59 +00:00
Maurice f128346a54 fix(tours): the other ways of a leg follow the points of the call that asks for them
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.
2026-10-24 02:18:08 +00:00
Maurice 5bf6af7afc fix(tours): new points of a saved hike take each saved point once and keep its shaping mark
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.
2026-10-24 02:18:08 +00:00
Maurice 1a941a6f1d fix(tours): a recorded track is neither turned round nor closed by update_tour
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.
2026-10-24 02:18:07 +00:00
Maurice 7e5b23808d fix(assistant): the home chat leaves a journey's own writes to the journey
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.
2026-10-24 01:41:36 +00:00
Maurice bfcc205f05 fix(assistant): a change left waiting past its day no longer holds the next one back
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.
2026-10-24 01:41:36 +00:00
Maurice a6a9f3bbdd fix(deps): multer, undici, nodemailer and fast-uri past the advisories published overnight
multer 2.5.0 (GHSA-q7qp-rjg7-q26m), undici 7.30.1 and 8.12.3 (GHSA-4qv8-2p9j-2685,
GHSA-f72v-6w45-q472, GHSA-xjj6-f33q-929c), nodemailer 10.2.1 (GHSA-8c8m-p3m8-cjg8,
GHSA-m943-m63m-w62w, GHSA-85x2-q946-cp5h) and fast-uri 3.1.9 (GHSA-w74x-v6f9-j3xg and
three more). The server's own ranges and the root overrides hold the fixed versions as
floors, the nested undici of isomorphic-dompurify's jsdom included.
2026-10-24 01:40:57 +00:00
Maurice 5651c11803 feat(assistant): the book designer works from a brief, with archetype covers, lively spreads and stickers
- 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.
2026-10-24 01:14:03 +00:00
Maurice 49f7a447d3 feat(studio): decorated templates, 21 covers and 16 spreads laid on any page in the book theme
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.
2026-10-24 00:36:00 +00:00
Maurice cbf9325e7e fix(studio): the book tools state every field once, and the server typechecks within its memory again
- 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.
2026-10-23 22:08:13 +00:00
Maurice 75d0593198 feat(studio): text effects, fit to frame and 24 lockups in a Text styles shelf
- A text can be cased (capitals, lower case, small caps), placed at the top,
  middle or foot of its frame, outlined, given a hard shadow or a marker band,
  bent on an arc or round a circle, filled with a gallery photo or left
  hollow, and shrunk to fit its frame. Every effect prints as vector: copies
  and strokes for HTML type, textPath and a clip over an <image> for SVG.
- Fitting is solved when the text is edited, in the Studio and in the edit
  engine, and stored; the chosen size is kept as the ceiling.
- Text sizes reach 400 pt and tracking 1.5 em.
- The Elements panel opens on a Text tab: the plain styles and 24 lockups
  (titles, badges and stamps, chapter marks, quotes, captions, places), each
  drawn with the book's own title and placed as one group.
- The assistant sets every effect through style and add, places a lockup with
  add_lockup, reads the effects in describe_book_page and gets two new
  findings (curve_overflow, effect_heavy) beside photo-fill and band checks.
- Book format revision 6.
2026-10-23 22:08:13 +00:00
Maurice 82b8eb1067 feat(studio): book themes with palette, font pairing and motif set 2026-10-23 22:08:13 +00:00
Maurice ce9c94a77b feat(studio): a second shelf of shapes, cut edges and a drawn line with heads and ornaments
- Fifty more shapes: arches, paper cut-outs (leaves, coral, weed, organic
  circles, a wonky star and sun), stamps, a postmark, a rosette, tags and
  ticket stubs, sunbursts, ribbons and bands, speech bubbles, drawn arrows,
  hearts, stars, photo frames and ornaments (scroll, laurel, fleuron, corner).
  The broad ones are photo frames too, and each tile is drawn at its shape's
  own proportions, which a new shape is also placed at.
- A cut edge on rectangles, circles, arches and the other broad shapes, painted
  or not, and on a photo's cut: zigzag, scallop, a postage stamp's perforation,
  wavy, torn and deckle, with a depth in millimetres. Cut in millimetres, so
  holes stay round on a wide frame.
- A line element: two to 32 points dragged on the canvas (a handle pulled from
  the middle adds one, a double-click removes it), straight or curved, solid,
  dashed or dotted, a wave or a zigzag, a hand-drawn wobble, a head on either
  end and an ornament in the middle. A shelf of lines and dividers places them.
- The assistant reaches all of it: add and style take the line (its points on
  the spread in mm) and the edges, describe_book_page says them, and two new
  findings say when a line is too thin to print and when an edge is set on a
  shape that takes none. A photo's mask is checked against the shape set
  rather than listed again, which keeps the page edit's schema smaller.
- BOOK_SCHEMA_REV goes to 6.
2026-10-23 22:08:13 +00:00
Maurice 7a7876b9f4 feat(studio): photo look with border, hard shadow, zoom, mirror, adjustments, duotone and cutout
Photos get a look beyond crop, mask and frame style, in Studio and for the
assistant alike:

- border (width and colour, following the mask or the corner radius), a hard
  offset shadow and a die-cut cutout edge, all flat vector shapes in print
- zoom 1 to 4 about the focal point and a left to right mirror
- brightness, contrast, saturation and warmth, and a duotone; these are
  filters, labelled raster in print in the inspector
- the print resolution of the selected photo in the inspector, with a warning
  under 200 dpi, measured from the original

PhotoView moves out of SpreadView into its own file and uses per instance
SVG ids, so a spread drawn twice keeps its clips and filters apart. The style
operation takes the look, describe-spread lists it, the dpi and crop findings
account for zoom and mirror, and a new raster_effect finding notes filters on
a large photo. BOOK_SCHEMA_REV goes to 6.
2026-10-23 22:08:13 +00:00
Maurice 9b8626622f fix(deps): zod at 4.6.7 across the tree, jimp's copy included
Zod before 4.6.6 can exhaust memory while it validates an oversized
constrained collection (GHSA-mrhx-c7xc-m3w5), and every request body and
tool call goes through it. The workspaces ask for 4.6.7 and the root holds it
as a floor for the whole tree, so jimp, which pins zod 3 and has no release
on 4, resolves to the same copy. Its option schemas use only object, number,
tuple, literal, union, nativeEnum, boolean, string, instanceof and array,
all of which zod 4 keeps; resize, scaleToFit, crop, cover, contain, blit,
composite, rotate, flip, quantize and the jpeg and png encoders run on it.
2026-10-23 22:06:45 +00:00
Maurice 31dba65906 fix: the last red checks after the tour, home and place picture merges
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.
2026-10-23 22:40:14 +02:00
Maurice 8c7fc989dc fix: the merged tour, home and lightbox changes pass their checks
The demo gate test allows wanderer as the parity harness does, the open tour
store is listed in the store registry, the trip chat card's test reads the
dates and not the question's hidden label, the lightbox leaves the rtl
baseline, and the tours module is formatted.
2026-10-23 22:19:23 +02:00
Maurice 58204e72bd fix(ai): a ChatGPT turn that searched the web goes on after a tool call
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.
2026-10-23 22:16:22 +02:00
Maurice 5d334d7ec8 feat(assistant): the assistant opens outside a trip, as a home chat about all trips
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.
2026-10-23 22:00:06 +02:00
Maurice cd60d4d859 feat(tours): assistant takes found places into saved tours and route files from the chat
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.
2026-10-23 22:00:05 +02:00