TREK's code for Brazilian Portuguese is 'br', which Intl reads as Breton.
The assistant passed it straight to Intl.DisplayNames for the system
prompt's answer language and to the card formatters, so the model was told
to answer in Breton. Convert TREK codes to their BCP-47 tag with
getIntlLanguage before handing them to Intl.
Closes#2800
A token whose account has no local ActivityPub author was reported as
invalid_response, which the settings show as 'The answer did not come from
wanderer', although wanderer had answered fine. It now has its own code,
no_author, with a message in every language that says what is missing.
A failed wanderer call kept its reason in WandererError.detail (the field that
did not match, or what came instead of JSON), and the client comment said it
stays in the log, but nothing wrote it anywhere. The log only had the generic
'wanderer answered with something TREK does not understand', so neither an
admin nor we could tell what wanderer had sent. Every refusal now logs its
code, message and detail.
gpt-5.6-sol, gpt-6.1-sol and the other reasoning models refuse function tools
on Chat Completions, so every assistant message on such a model came back as
HTTP 400. An OpenAI connection whose model is from the o-series or GPT-5 and
later now goes through the Responses API, the client a ChatGPT plan already
uses, with the key as its bearer token and no token refresh on a 401. Older
models and the -chat variants stay on Chat Completions.
Closes#2792
Sonnet 5.5 and Opus 5.5 think by default and write what they say between tool
calls into thinking blocks, which they want back unchanged with the rest of
the turn. The client dropped those blocks (and their signatures) and rebuilt
the turn from its text and calls, so after a tool result the next step came
back empty and the assistant gave up with empty_answer. A turn that thought
is now replayed block by block like one that searched the web; the cache mark
before the question skips a thinking block, and replayed blocks are copies so
a mark never sticks to the stored answer.
Closes#2789
The model picker in Admin > Addons did nothing for a ChatGPT connection: the
only way to change the instance's model was saving the connection again, which
needs an API key a plan does not have. A PATCH /api/admin/ai/connection/model
now switches it on its own, to a model the provider offers.
Closes#2783
The overview of a trip's tours decides for itself when it shows, which keeps the planner page hook inside its complexity and length limits, and adds nothing to the camera's key while there is no tour to frame. The elevation helper names its empty case for the strict type check, the self-host wording exemption for the retired Dawarich card goes, the day plan test reads the wrapping pills, and the new tests drop their non-null assertions and loops.
The update dialog now shows the 5.0.0 headliners, Tours, TREK Studio, the assistant and help on every screen in 27 languages, each with a drawing of its own, translated into every language TREK ships. The 4.3.3 cards and their drawings are gone.
Dismissals were compared with the prerelease part dropped, so a notice closed on 5.0.0-pre.2 counted as closed on 5.0.0 and the final release showed nothing to anyone who had tried a prerelease. Versions now compare in full.
Each member's amount was converted and rounded to a cent on its own, so four 34,000 ISK quarters of a 136,000 ISK bill came to 997.52 EUR against the 997.51 the payer was credited. The balances ended a few cents off zero and settle-up had no payment for them. A split whose amounts match the payers in the bill's own currency is now converted as one set by largest remainder, in the settlement and in the per-person summary alike.
Six upload routes refused the shared demo account in demo mode; journey photos, videos, gallery media and covers, collab note files and chat images did not, so any visitor could put images in front of every other one for the hour. They answer the same 403 now, checked in the handler after the upload is read, and a text-only chat message still goes through. The Demo Mode wiki page lists them, and says document sync is not covered.
The hourly reset puts only the database back, so a cover, photo, place image or trip file a visitor deleted in between was missing from the restored rows for good. On a demo instance StorageService.delete now leaves the content categories alone; the caches, the backups and the assistant's attachments are still deleted, and the orphan thumb sweep no longer counts a kept thumb as removed.
The trip Photos addon of old releases is still seeded, switched off, and nothing reads it any more. The policy test now fails on no row, and its checks run without awaiting in a loop.
One UPDATE per shelf and state and one upsert for the switches, inside the same transaction, and the demo account's settings in one upsert. The two new log lines go through the logger.
The seed put the example trips in whenever the admin owned none, so a demo
whose content belongs to the demo account got them back on every reopen,
the hourly reset included, and the next baseline saved them along.
The client is about to lock settings sections for the shared demo account,
and it has to ask the same question the server does. DEMO_ACCOUNT_EMAILS and
isDemoAccountEmail now sit in @trek/shared, and the server's DEMO_EMAILS is
built from them instead of spelling the two addresses a second time.
A demo instance now runs with one explicit addon policy (demo-addon-policy.ts)
instead of whatever its admin last switched: every trip, global and
integration addon on, and off only what reaches a server of the visitor's
own, the five document sync providers, wanderer under Tours, the Immich and
Synology Photos providers, AirTrail and Dawarich. The switches under the
addons (Tours maps, piste routing, bag tracking, the collab features) are on.
The demo seed applies it, together with the demo account's English
language, on every boot and after every reopen, and the hourly reset applies
it once more after the baseline swap, in one transaction each. A test pins
that every seeded addon and provider is named in exactly one list, so a new
addon has to be classified before it ships.
Every visitor of a demo instance signs in as the same account, so one
visitor's API key, MCP token, OAuth client, passkey or new email address
became everybody's. These writes now answer 403 for the demo account through
refuseForDemoAccount in demo-write.ts: creating API keys, creating and
deleting MCP tokens, registering, rotating and deleting OAuth clients,
approving an app and ending a connected app, changing the name, address or
picture, and enrolling, renaming or deleting passkeys. Password, 2FA,
account deletion, sessions and the own AI connection were refused already.
The demo account's language is fixed to English: a single settings write of
the language answers unchanged, a bulk save drops it and keeps the rest. The
MCP settings tool is held back for the demo account by the tool gate, as
every write tool is. The admin of a demo instance and every real instance
are untouched.
A stay taken into a journal now has a card of its own, so ASTTOOL-001
looks for its tool; Dawarich's tools are listed only with its addon on,
which the test now turns on beside the others.
The journal header's tool list was a value read only for its type, so it is
a union now. A journey's session reads the entries a call names side by side,
the photo announcements go out together, and a photo move links its photos
one after another through a promise chain, so each still takes the next
place among the target's photos.
isHeldInJourney took every tool of the journey's controllers from the Studio
side, delete_journey among them. The Studio never offered it (its writes are
the book's), so leaving it unattached changes nothing the model sees and
keeps the denial in one place.
A Dawarich stay's row read fields one side of a union did not have, the
photo cards narrowed an entry's day through an optional chain, and the
settings service cast a journey row straight to a record. Helpers only
their own file reads are no longer exported, and the photo tests seed
their rows with insertRow like the other journey suites.
The four new photo link tools join the journal's tools: the journey chat
offers them to editors, the trip chat loads them with the journey group and
the home chat keeps none. A journeyPhotos card shows the photos as
thumbnails with the entries they leave and reach, the first one marked as
the cover in a new order, and a caption old to new; a library add shows the
photos once they landed. A linked photo comes off again, an unlinked one
goes back, moved photos go back and a caption is written back, each while
nothing changed since. A new order of an entry's photos and a library add
have no way back yet. The journal prompt names the photo tools.
Linking a gallery photo to an entry and taking it off told nobody, so other
tabs, and the journey page after an assistant change, stayed as they were.
Both now go through a photo links service that broadcasts
journey:entry:updated after the write, with the asking socket left out on
REST; a caption change through PATCH photos/:id broadcasts journey:updated
the same way. The service also moves photos from one entry to another of
the same journey in one transaction, as POST
/api/journeys/entries/:entryId/photos/move, with a strict contract. The MCP
tools link_journey_photo, unlink_journey_photo, move_journey_photos and
set_journey_photo_caption call the same methods; the caption tool answers
the caption it replaced.
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.
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.
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.
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.
Allan Braun