- A job of five or more real steps is looked back on after the answer: the short way that
worked becomes a skill (or improves the one it followed); the reply says so. The prompt has
the bot check its skills before starting.
- Upload, download and PDF on Bot 的電腦's browser look for and save files in the box, not on
the brain (a picture in a Threads post took 24 steps).
- The bot's browser keeps the six tabs used last (19 Threads tabs had filled the box's 2 GB).
- Words name the control, not the box around it: a form's 「Customer name:」, 「Large」 and
「Submit order」 used to land on the <p> holding them and do nothing.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uirha2RVfSYmrhqNnqx9Z4
From the second round of real runs:
- Direct mode no longer asks the model to check "always ask" rules before steps that only look
(screenshot, showing the screen, reading a page or file): none of those rules can be about them,
and the check cost each look at the person's Mac 10-20 s. Clicks and typing are still checked.
- An error inside the model's answer stream ("The model is currently at capacity…") is retried after
8 s and said in Chinese; it used to become the bot's reply, in English, never retried.
- send_file says it sends from any computer, the person's included (the bot copied a file to its own
computer first, which only works for text).
- A shown screen's file name carries no time (a server's clock is UTC).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uirha2RVfSYmrhqNnqx9Z4
From real runs on the cloud brain with the person's Mac (Threads patrol, a post draft, "show me my
screen"):
- computer_use_show: a plain picture of any computer's screen goes into the chat (the bot sees it
too). The bot used to describe a screenshot in words and fail to send it.
- The phone shows the bot's attachments: pictures in place, other files download on a tap (api/file,
only from the chats' file folder). It showed nothing for the bot and names only for the person.
- send_file works from the person's other computers (fetch_file over the relay, 20 MB, secrets stay).
- The same call with the same answer again and again is warned the 3rd time and stopped from the
4th (a blank tab was read 11 times, then the bot said Threads was logged out without opening it);
a blank tab says so; checking a login means opening the site.
- Screenshot lists: a nameless row around a named button isn't numbered, a nameless row takes the
words inside it, empty spacer rows aren't numbered (System Settings: 63 numbers -> 33, all named).
- Writing "in my voice" reads the person's own recent posts first.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uirha2RVfSYmrhqNnqx9Z4
Web
- web_fetch kept pages with a <header> only up to it (taken for <head>): articles came back as their menus.
- browser_open waits for the page to load and returns it like browser_read (one step fewer per page);
actions wait for the page to hold still instead of fixed 1-2.5 s sleeps; one way to reach the tab.
The bot's computer (box v6)
- Numbers only on what can be seen: clipped to the window and the page's visible area, none under
another app's window (a link scrolled under the toolbar was numbered on Back).
- press_key with a typed character no longer swallows the keys after it (xdotool type --args 1).
- The person's input through noVNC/TigerVNC is noticed again (fence, continuous updates, QEMU keys).
- "Nothing changed" only after clicks, scrolls and drags; long text is pasted; one screen step at a
time; one docker inspect per step when the box is known ready; poppler-utils for long PDFs.
- One typing path and fewer round trips (stdin variant, unused picture path, extra batch execs gone).
The person's computers
- Linux: the window system's front app when it has one, and the reason when there is none (was 「」);
hidden and off-screen controls get no number; wording no longer names a tool that doesn't exist.
The loop
- Without Docker, the bot's own computer runs no commands where there is no sandbox (Linux, Windows):
it was a plain shell on the brain itself, keys in reach, asked nothing.
- The bot's own computer is re-checked each step; unreachable computers are failures, not safety
blocks; no direct-mode note on every result; an empty reply is asked again; scrolling and keys
aren't counted as going in circles; steps aren't moved to a computer that can't do them.
- One finish() for every step's result, keep_grant(), dead appctl list_computers/SERVING and the
impossible server branches removed; duplicated prompt instructions merged.
Tests: 162 (Mac) / 166 (Linux) unit; real box drills 6/6 on box v6; a brain without Chrome browses
on its box; remote E2E 28/28.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uirha2RVfSYmrhqNnqx9Z4
- A turn may take up to 100 steps (was 25, which cut off real work; Grok Bot sets no limit).
Every 25 steps the bot is asked whether it is still getting anywhere.
- The system prompt asks for independent tools in one step and combined commands.
- Browser steps for the box always go to the box's Chromium. They used to depend on whether
the brain itself had a Chrome, so a cloud brain sent them to "the person's browser".
- The box's DevTools forward passes bytes with a plain read/write loop. std::io::copy splices
on Linux and held back short requests, so the box browser never opened from a Linux brain.
- A gateway's HTML error page shows as plain words.
- Real test a_brain_without_chrome_browses_on_its_box (ignored): passes in a Linux container
with no Chrome against a real box, and fails without the routing fix.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uirha2RVfSYmrhqNnqx9Z4
A bot asked to open a Threads profile clicked an empty strip ten times: it guessed coordinates
from a picture, and the web tools' description told it they didn't work on its own computer.
- marks.rs: the picture a bot gets has every button, link, field and menu item boxed and
numbered (a tiny built-in digit font, pure Rust), with the same numbers in a list. click /
typing / scroll / mouse_move take the number (ref) and land on the control's centre.
- Where the controls come from: macOS AX and Linux AT-SPI through agent-desktop on a person's
computer (desktop::elements); AT-SPI in the bots' own computer (box/a11y, after XBot's
box-a11y), web pages included. On a Mac a control whose spot another app's window covers gets
no number (topmost window at its centre must be the app's; the Dock's invisible full-screen
window doesn't count). open_app waits until the app is really in front.
- No going round in circles: a step that changed nothing says so; the same step (clicks within
16 px) a third time in a turn comes with a warning, from the fourth time it isn't run.
- The box (version 4): one TigerVNC server instead of Xvfb + x11vnc, the AT-SPI bus and registry
at boot, one browser launcher (box/browser, after XBot's box-chrome: same profile and CDP,
renderer accessibility, a launch lock, stale profile locks cleared). One docker exec per look
(list + picture, ~0.4 s). A brain updates an older box by itself when it has been idle a
minute (files and logins stay); a new box is never made from an older image.
- Gone: computer_use_read_app (the list is in every picture), computer_use_mouse_button, the
per-call picture for the phone (it gets a plain one), the stale browser_read note; the prompt
says web work goes through browser_* by number, and never to read browser cookie or history
files.
Tests: marks (numbering, drawing, fingerprints), box_numbers_are_exact on a box from the new
image (a Threads-like page: the icon links get numbers, Profile clicked by number, Chinese typed
into the numbered field, a click on nothing called out), box_screen_is_exact, VNC e2e 11/11 on
TigerVNC, Calculator 7×8=56 by numbers through the signed app on this Mac, remote_e2e 28/28,
153 unit tests; Linux build + 157 tests + x11_live.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A turn started from the phone (not a computer) kept 「don't know」 for its whole run: a message
typed on the Mac while it waited on a hand-off had its 「我的電腦」 moved to the bot's own computer.
Each step now asks which computer the person last typed on, and the brain keeps it beside its
data (person-computer.txt) across restarts. remote_e2e: a second computer, and a mid-turn
message from the other one (fails without the fix); 28 checks.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- The brain looked the account's computers up once a minute: for up to a minute after the Mac
came on, 「我的電腦」 was unknown and steps went elsewhere. Now every 15 s, and at once when a
message comes from a computer it doesn't know yet.
- A step naming a computer that is off says so in words instead of running on the chosen one
with a note that the person hadn't asked.
- Snapshots: tar's 'file changed' (the open browser) is not a failure; browser caches are left
out; ten minutes for a large home folder.
- box_end_to_end clicks the terminal where it opened; restore only with ANYBOT_TEST_RESTORE=1.
- deploy/test/remote_e2e.py: account server + headless brain + hands + scripted model, 27 checks
(computers, redirect, agent-desktop on the hands, hand-off 3 ways, phone view, sync copy,
edits, hands offline/back, brain restart, clear). anybot --sample-state for such tests.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- hand_over_computer (the original's box hand-off card): instruction, live screen with 接管,
跳過 / 我完成了 / 接管; 我完成了 also in the viewer; a typed message answers it too. Header,
sidebar and notifications say 等你處理 / 「{name}：需要你」; the phone shows it with 接管.
- Mac: the content reaches the top (no grey title bar); the top strip drags the window.
- Panel 電腦 card: each line stops before the picture; the brain's name on its own line.
- Viewer: buttons first, the title ends in … when narrow; the picture is centred.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- A bot's own computer is 「<bot> 的電腦」; this one and the account's others go by their names.
The server brain picked 你的電腦 by sorted host id, so a desktop left on the server won.
- 「我的電腦」 is the computer the person typed on (the relay names it); unknown means ask.
- A step moved back to the chosen computer tells the bot so.
- Composer chip and bot settings choose the computer by name; a screen asks the brain.
- A screen's 電腦 card and viewer show the brain's computer, not this one's box.
- A screen's chat copy that falls short asks for everything again instead of appending;
清除聊天記錄 on a screen clears the brain's chat.
- Model requests to a private address go through the person's computer first.
- Phone typing on the box sends the text the tool reads.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- A brain that can't reach a model at a private address (e.g. Qwen at 10.x) sends the request
through its hands; the hands only forward to addresses on their own network, and only for
their brain (uses the existing device channel, so the account server is unchanged).
- The computer chosen for a bot is binding: a step naming another computer goes to the chosen
one unless the person's message names that one (「在我的 Mac 上」).
- Browser steps follow the computer: Bot 的電腦 drives the Chromium on its own desktop (through
docker exec, no new port), 你的電腦 its browser; before, they always used this computer's.
Checked: on this Mac, Bot 的電腦 browsing opened example.com in the box's Chromium and an
unasked 你的電腦 command ran in the box; 「在我的 Mac 上」 ran on the Mac. Linux brain in Docker
with 10.0.0.0/8 blocked + this Mac as hands: model calls went through the Mac, shell on
你的電腦 answered from the Mac, browser defaulted to the Mac's.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- 語言 繁體中文: a reply's Simplified characters are turned into Traditional with Taiwan
wording (zhconv), since some models (Qwen) slip despite the instruction.
- A brain on a server: browser steps go to the person's computer (its hands) unless the
server's own browser is named; 你的電腦 is listed first.
- update_bot says the default computer it set.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A brain on a server has no AnyBot browser, and browser_open/read were sent to it even when
the bot named a 手腳 computer. Now a named computer wins, and with none named the hands'
browser is used.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uirha3oEtWeHh58zA7ErHa
computer_use_* name the computer whenever the screen is another computer's, and with no
computer named the step goes to a screen that is really there (the bot's desktop, this
computer's, then a 手腳 computer) instead of a brain's missing one.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uirha3oEtWeHh58zA7ErHa
- The brain's bots get computer_use_* for 手腳 (devices), as the prompt already said; before,
they only had shell there and fell back to scrot, which can't see a Wayland desktop
- After saying yes in the 「使用電腦工具」 pop-up (it shows the step), that same step isn't asked
again (sending messages still asks every time)
- A certificate failure says so instead of 「網路連線出了問題」
- install.sh restarts the background AnyBot after an update
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uirha3oEtWeHh58zA7ErHa
- Brain answers /api/sync (per-screen deltas of settings and messages),
/api/sync/edit (small edit operations) and /api/sync/act (chat actions).
- Relay forwards host-to-host sync requests within one account (role mirror).
- Desktop: choose a brain in 手機與帳號; its own bots are kept aside; offline
shows the last copy read-only and reconnects by itself.
- Keys and tokens stay on the brain (redacted and restored on edits).
- Browser tools can run on another computer of the account (computer arg).
- anybot --serve: ANYBOT_DEVICE_LINK=1 and ANYBOT_BRAIN=名稱.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uirha3oEtWeHh58zA7ErHa
Rust/egui rebuild of Grok Bot as of 2026-11-04: chat with streaming
providers (xAI, OpenAI, Claude, Gemini, OpenRouter, OpenCode Go, Ollama,
custom), tools and approvals, the bot's Docker computer, computer use on
macOS / Linux X11 / Wayland, AnyBot's browser with a full DevTools-based
toolset, the encrypted vault, pinned grid and sidebar sections, Markdown
with Mermaid diagrams, phone access through the relay, and the Linux
build and test scripts.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uirha3oEtWeHh58zA7ErHa
王性驊