Bots learn what they did; the box browser's files and tabs; words reach the control they name #6

daniel.w · 2026-11-06T15:57:20Z

daniel.w commented

2026-11-06 15:57:20 +00:00

After a job of 5+ real steps the bot keeps the way that worked as a skill and checks its skills before starting (real Grok test: 2nd run used the skill, 10 steps in 24 s). Upload/download/PDF on Bot 的電腦 use the box's own disk (a picture in a Threads post took 24 steps). A finished job closes the tabs it left open (the box was at 1.99 of 2 GB with 28 tabs). Text targeting picks the named control instead of the

around it. 172 tests pass; deployed to 10.0.0.25 and nobledesktop. 🤖 Generated with Claude Code https://claude.ai/code/session_01Uirha2RVfSYmrhqNnqx9Z4

After a job of 5+ real steps the bot keeps the way that worked as a skill and checks its skills before starting (real Grok test: 2nd run used the skill, 10 steps in 24 s). Upload/download/PDF on Bot 的電腦 use the box's own disk (a picture in a Threads post took 24 steps). A finished job closes the tabs it left open (the box was at 1.99 of 2 GB with 28 tabs). Text targeting picks the named control instead of the <p> around it. 172 tests pass; deployed to 10.0.0.25 and nobledesktop. 🤖 Generated with Claude Code https://claude.ai/code/session_01Uirha2RVfSYmrhqNnqx9Z4

daniel.w added 2 commits 2026-11-06 15:57:20 +00:00

cbada6bdb1 Bots learn from what they did; the box's browser works with the box's own disk

- 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

b480ea16dd A finished job closes the tabs it left open, keeping the page it ended on

Every browser_open is a new tab and nothing closed them. When a job ends (answered, stopped
or failed) each bot browser it used keeps only its front page; a browser that isn't open isn't
started for this, and one another job is still using is left alone. The six-tab limit stays
for long jobs.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uirha2RVfSYmrhqNnqx9Z4

daniel.w added 4 commits 2026-11-06 16:36:36 +00:00

4605b317d8 Bot 的電腦 can run under gVisor: its own kernel, Chromium's sandbox back on

容器隔離 in 設定 › 電腦: standard (runc, the container is the only wall, Chromium runs
--no-sandbox) or hardened (runsc: a virtualized kernel, all capabilities dropped but the few
the desktop needs, ANYBOT_BOX_SANDBOX=1 turns Chromium's own sandbox back on). Box image v7.
deploy/mac/gvisor-vm.sh makes a Lima VM with Docker + gVisor for a Mac (started at login),
gvisor-migrate.sh moves the box's files and logins there.

Checked and finished before committing:
- the hardened choice is offered only on a Docker host that has runsc; a box set to it on a
  host without it opens the standard way and says so (it used to not start at all)
- the settings row shows what the box really runs on, and when 更新 is needed
- no swap only under gVisor (a standard box keeps Docker's default)
- the migrate script sees the running Mac app ("AnyBot", not "anybot")
- the VM script starts an existing VM by name, checks runsc and the kernel from the Mac
- the version test says 7

Real run in the Lima VM: desktop, VNC, numbered controls, xdotool and screenshots work; no
Chromium process has --no-sandbox, renderers run with seccomp and their own namespaces.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uirha2RVfSYmrhqNnqx9Z4

9a23411e51 Checked by using it: tests stay off the real box, gVisor scripts run clean, times are the person's

- box_numbers_only_on_what_is_seen is ignored again (a test inserted before it in cbada6b took
  its mark: every cargo test drove the real box), and the path test runs
- gvisor-vm.sh restarts the VM's Docker only when runsc was just registered (a restart stopped
  Bot 的電腦), and `${var}` before full-width text (bash read 「）」's first byte as part of
  the name and stopped)
- a scheduled box update and a PDF's name use the person's time zone (a server keeps UTC)
- 容器隔離 lists 標準 before 強隔離
- screenshots of real data can open 設定 › 電腦 (ANYBOT_SHOT_VIEW=computers) and scroll
  (ANYBOT_SHOT_SCROLL)

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uirha2RVfSYmrhqNnqx9Z4

19f8257e48 An upload says what the field holds now and what the page showed

The tool only said it put the file in; on a page that shows nothing about it the bot spent five
more steps checking (shell, read, screenshot, two scripts). Now the result names the file the
field holds (and its size) and the page's new text, and an empty field is an error. Real run in
the gVisor box with Grok: the sign-up form went from 10 steps / 35 s to 6 / 20 s; the second
time it followed the skill it had learned, by names only, 6 steps / 21 s.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uirha2RVfSYmrhqNnqx9Z4

e0a1545e0e A step on a skill or a memory says which one

The phone showed a bare 「刪除技能」 when 新 Bot deleted the test skill; save/use/delete skill,
remember and forget now carry the name or the fact.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uirha2RVfSYmrhqNnqx9Z4

daniel.w closed this pull request

2026-11-06 16:58:29 +00:00

Pull request closed

Please reopen this pull request to perform a merge.

Sign in to join this conversation.

No reviewers

No Label

No Milestone

No project

No Assignees

1 Participants

Notifications

Due Date

The due date is invalid or out of range. Please use the format 'yyyy-mm-dd'.

No due date set.

Dependencies

No dependencies set.

Reference: daniel.w/AnyBot#6