The server kept voice and images on /v1 (models scope, which the app's token
already asks for); /me's services and scopes decide what is offered. Rust
sends the recording to /v1/audio/transcriptions, reads /v1/audio/speech back
as a data: URL (CSP media-src data:), and for /v1/images/generations takes
only the id of each of the person's own files from the answer and fetches
/v1/files/<id>/content from the app's own server. The microphone is allowed
only within seconds of the page's own Dictate (voice_arm); WebKitGTK's
media stream is switched on through its settings getter.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Files -> Server writes through /api/v2/files/{upload,mkdir,rename} and
DELETE /files (the trash); upload is a Rust command (library_upload) that
picks files in the system dialog and sends them multipart in the field
`files`. A chat's menu opens Tools and skills..., the web's chat-settings
switches over GET/POST /chats/{id}/scope and /allow/clear. A popover can
open at a context menu's point.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The account's memory as the web's Settings -> Memory keeps it: add, change,
remove, over /api/v2/memories. Ctrl+K asks the server's search once two
letters are typed and lists the hits below the titles, the matched ranges
drawn as <mark> elements over plain text.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The server's /api/v2 sets `pinned` on PATCH /chats/{id} and makes, renames and deletes
folders. The sidebar lists the pinned chats first, then the folders (nested, folded as the
server keeps them, each counting its chats), then the rest by day; searching lists every
match flat. A chat's menu pins it and moves it (to no folder, any folder, or a new one);
a folder's menu renames it, makes one inside it, deletes it (its chats stay). Tests F8.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The server's /api/v2 now has PATCH /me {language, theme} and /me lists its languages and
themes. The theme is the account's and choosing one saves it there (a refusal is said);
a server whose /me lists no themes keeps the earlier choice in the app. The language is the
account's unless Settings chose this computer's or another (kept in the app, as the phone
does); a change of the account's opens the window again in it, once.
Fixtures re-pinned to the server's dev (f7f2ff2), with the new /api/v2 parity ones.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Appearance in Settings chooses the language (the system's, or one of the nine the app has;
the window opens again in it, its replies and shells let go first) and the theme (the
account's, or Moria or Shire, drawn at once and the window painted in it). Kept in
localStorage on this computer: /api/v2 has no PATCH /me for either yet, so the account's
own stay as they are. i18n.js reads the choice and carries each language's own name from
the server's catalogue. Tests E5.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Where the account has another computer linked (GET /devices), a chip before the folder
chooses it; this computer stays the default. Its folder is one its agent chats have worked
in, or a path typed in; the Terminal before the first message opens there too. Tests D4;
failing UI tests are also GitHub annotations.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Archive was one-way in the app. Archived (sidebar, under Files) reads
GET /api/v2/chats?archived=true, newest first and paged; a row opens the
chat, Restore chat PATCHes archived:false and reads the sidebar again, and
the row's menu deletes. An open archived chat says so in its header, with
Restore chat there and in its menu. The words are the web's own ("Archived",
"Restore chat"). Tests: D2 at 1280 and 390 px.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
On the server's /api/v2 (3.4.0, server dev 5d7b79c):
- The activity panel reads GET /chats/{chat}/tree beside the activity and
draws ui/js/tree.js's rows in a Subagents section, the server panel's words
and layout: nested by parent, position, phase, context %, state, model,
mode + request options, messages and the last one, open slots, the ended
ones folded and dimmed. A team's members are no longer drawn again among
the tasks. The stream's `tree` frame redraws it.
- A subagent's conversation (/subagents/{id}/transcript, read again every 3 s
while it works) and its findings open read-only in the panel; Stop asks,
then POSTs /stop. With an agent chat's device away: the kept tree with the
server's note, and its 409 sentence for the rest.
- A new agent chat's Subagents chip from /models?kind=agent&device= (each
model's `subagents`, `agent_subagents.offered` and `device_runs`); an open
agent chat's from its own `subagents`, as before.
- An approval item's `subagent` names it on the card.
- Progress keys are the spec's own ({{field}}), as the server's catalogues
have them; SERVER_PENDING is gone, every sentence is translated.
tests/ui reads the server's contract fixtures (scripts/fetch-fixtures.sh ->
tests/ui/fixtures, SOURCE says the commit): status frames, tree, tree frame,
transcript, findings, models?kind=agent, a subagent's approval; six C4 cases.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
ui/js/progress.js draws harness spec 3.4.0's `progress` (progress.md) with the
spec's texts as the page's sentences: the thirteen phases, their variants and
field words, the line with its clock in whole seconds (5s, 1m 05s, 1h 02m),
none for stopped and failed, retrying counted down. A live reply takes
`progress` from any stream frame that carries it and ticks once a second; with
no progress (an older server, or null) it draws the status text as before.
The sentences are the server's to translate: gen-i18n.py takes them from its
catalogues once they are there (SERVER_PENDING), English until then, without
failing.
tests/ui: every case of the spec's conformance/progress.json (copied, 3.4.0),
and a live stream's progress, clock, fallback and stopped line.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The Terminal panel opens a shell on the device an agent chat works on, in its
folder: for a new agent chat as soon as the device and folder are chosen (the
server's /api/v2/devices/{device}/terminal/ws?directory=, which the chat's first
message takes over -- the same socket carries on), and for an open agent chat
from the header (/api/v2/chats/{chat}/terminal/ws, the web page's shell).
Offered where GET /devices says the device opens a terminal.
The socket is Rust's (src-tauri/src/terminal.rs, tungstenite on the rustls
ureq already brings): the bearer token goes in the handshake and never reaches
the page, which gets the frames as `terminal` events and sends keys, sizes and
close through commands. 4401 signs the app out as a 401 does.
xterm and its fit addon are the server's vendored build, pinned through
fetch-vendor.sh like CodeMirror and loaded on the first open. Send to chat puts
the selection, the last marked command and its output, or the screen into the
composer, never sent. The terminal and the activity panel take turns in the
panel column. Continue in a terminal stays in the chat's menu.
tests/ui: seven B3 cases with a mocked socket, at 1280 and 390 px.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
An agent chat's bash approval left "Waiting for you to allow bash…" with no card: cardOf()
called append(actions, a, b, c) while append() took one array, so `children.flat` threw for
every approval and plan card (questions used el.append and worked). renderCards() had already
unhidden #cards, which stayed empty. append() now takes children as rest arguments too.
- The editable command is `detail` (services/device_link.py puts the fixed "Run a command" in
the title); it is sent back as the item's text only when changed. Non-editable approvals
show the title and the device's input. `purpose` ("It says: …"), `reason` and the asking
subagent (`job`) are shown, as on the web page.
- renderCards() keeps a card already on the screen (by id) instead of drawing every card again
on each `ask` frame, which the server re-sends whenever the countdown changes; a card that
cannot be drawn shows the error instead of an empty box.
- tests/ui/: headless harness with a mocked Tauri bridge; five A1 cases (device bash card
shows and is visible, Allow/edit/Deny post to /chats/{id}/interactions/{card}, redraw keeps
edits, reopen gets the card from the stream's first pass, 390 px).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The chip's popover is one range from 1 to the server's cap (subagents.cap, /models
subagents_cap, else 32) with two handles: two range inputs overlaid on one track, the span
filled, aria-labels Min and Max with value text, keyboard as any slider, Min never past Max,
the values said above it ("Min 1 · Max 4") and the two ends under it. "Fewest"/"Most" are
gone. The hint says what the numbers count: the chat's own agent -- 1 is the agent alone, Max 4
is the agent and up to 3 subagents. Untouched on a new chat it still leaves the server's
defaults (1-4, shown). i18n: Min, Max and the new hint in all eight languages. CHANGELOG.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Models' `subagents {offered, named_only}` and /models' `subagents_cap`; a chat's
`subagents {offered, named_only, cap}` decides the chip for an open chat (an agent chat
gets none where the server says so); `named_only` shows the spec's `own` line in the
popover and marks the chip. GET /chats/{chat}/team stays the fallback for older servers.
- Context: `auto_compact`, `until_compact` and `compactable` from the server (worked out from
`threshold` with an older one); Compact greyed while not compactable.
- "Tasks: N" for a task's nested fold, the server's sentence; the subagent words aligned with
the server's catalogues (Podagenti, Sottoagenti, Podagenci); hint says the same-model rule.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- "Subagents" everywhere a person reads it (chip, popover with Fewest/Most, scheduled task,
panel); offered per the server's `subagents` on a model or chat where it says it, else as
before; the fields' most is the server's cap, else 32. No subagent-model setting.
- Panel: always reachable from the header's button; the line above the composer only while
something runs; Environment for an agent chat; Context with "N until auto-compact" and a
Compact button (POST /chats/{chat}/compact; a server without it is said so); Background
tasks under Running with elapsed time and a stop square each, unfolding to kind, step,
live text and conversation, nested tasks folded under their parent, Finished N folded;
Room and Plan as sections.
- i18n: 24 new sentences x 8 languages, 9 retired; CHANGELOG [Unreleased].
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Re-wired to api/v2/schedules.py and its contract fixtures: description and
next_run(s), pause/resume verbs, runs paged with `before`, a run's result
(GET runs/{id}, Markdown) unfolded under its row, run.model with the switch from
a busy one, waiting and its retry, timing (late, caught up, by hand). The form
serves new and edit: words -> compile -> title, instruction and next runs; the
rule set by hand (days and a time, read back by preview) when the words give
none; notify policy, fresh or continue, model from the scheduling models,
effort and team size. Models on the list: the person's narrowing (PUT
/schedules/models), each free or busy. Live from the `schedules` event.
i18n: 39 new sentences x 8 languages (312 in all); CHANGELOG [Unreleased].
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
51 sentences of the app's own in all eight languages (gen-i18n.py OWN), the rest from the
server's catalogues; 11 sentences no page uses any more are gone. The title bar's pills stay
inside its height at touch sizes; a failed scheduled run has its own notification words.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Every new sentence in the nine languages: 54 more, of which all but four come
from the server's own catalogues (its activity panel, team setting and
Thinking switch use the same words); the four about continuing in a terminal
are the app's own, in all eight.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Attachments from the file dialog, a drop on the window (Rust holds the dropped paths; the page
never names one) or a paste (the bytes as the raw body of the call), sent at once to
/api/v2/attachments as multipart and shown above the composer.
- Edit message (rewind), Regenerate reply on the last reply, Copy on both.
- The chat's menu (header and a right click in the sidebar): rename, open in the web interface,
archive, delete.
- The chat's model and effort in its header; effort for a new chat. Model avatars coloured as
the server's stable_hue colours them (MD5 of the id, checked against Python), mixed into the
theme's surface so no colour is hard-coded.
- Ctrl+K palette over commands and every chat's title; Ctrl+N, Ctrl+,.
- The agent's new states in the page; 34 new sentences in all eight languages, the server's own
words where it has them; a Czech row that was Slovak; two untranslated strings.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- The app's device login asks for `app models` and, where discovery says
login.device.agent_scope, `agent_scope=models memory link` in the same
approval. The agent's token goes to the bundled CLI on stdin
(`lembas login --token-stdin --server <url> --json`) and is never kept
here; if the CLI does not take it, it is given up on the server. A
computer linked already keeps its link; a server without agent_scope
gets the old two steps.
- The server pane reads GET /api/v2/files and /files/content (mounts open
like folders; `withheld` shown in the server's words). The "not offered
yet" state is gone.
- A show card's file comes from GET /api/v2/chats/{chat}/show?node=&version=
or ?shown= as plain text (new `api_text` command, 1 MB cap); args.path is
read only for agent chats on this computer, locally.
- The gate is link protocol 3 plus app_api 2 (APP_API = 2), not the
server's version number, which says 1.7.2 on dev until its first beta.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Plain HTML, CSS and ES modules in ui/, no build step. The sidebar opens on agent
chats (this computer first), with chats on the server as the second tab; the
transcript draws the /api/v2 steps, follows a reply as it is written, answers
cards, and starts agent chats in one of the agent's folders. Two explorers kept
apart (this computer's, the server's) and a viewer: Markdown drawn by a safe
renderer that never parses HTML, code in read-only CodeMirror with the server's
token colours, HTML in the sealed frame, show calls opened in it. Settings for
the sign-in, the agent and its folders, notifications and updates; no admin
pages. Layout on fixed and shared tracks; the sidebar is a drawer below 48rem,
the viewer goes over the chat below 64rem. All 124 sentences in the server's
nine languages.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
scripts/gen-i18n.py writes ui/i18n.js from the server's catalogues where the
same sentence exists and from its own table otherwise; the pages pick the
language from the browser and fall back to English.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
HomerandClaude Opus 5.5