The prompt had grown to a policy document: 13 sections, the same rules
repeated across them, and a state vocabulary no tool accepts. It also
never mentioned the reply/task split, so the model would burn a reply's
8 tool steps on work that belongs in a 50-step task.
- Lead with work placement: answer directly, start_task for its own long
work, delegate_task for a worker, and say work is under way, not done.
- Replace the invented Requested/Queued/Verified list with the real
TaskStatuses and update_task.
- Name the 19 tools it tells the coordinator to use, and which tool
writes which instruction layer, instead of "the available tools".
- Give routines their own section; create_schedule was uncovered.
- Say each safety rule once, and keep the interrupt list short so the
prompt reads as proactive rather than timid.
- Drop the commented-out previous prompt: that is git's job.
The test asserted a heading and a section that no longer exist, so it was
already failing. It now checks the heading, the SiteData name, the
absence of em dashes, the real statuses, and every tool named.
The coordinator's default prompt was a page of job descriptions. It now
states the working rules it kept getting wrong: a queued task is not a
running one, a tool result is the only proof an action happened, an
approved text is written whole, and an explicit constraint such as "no
computer" is binding. The prompt is attached at creation only, so this
reaches new installs and a coordinator whose prompt is still empty.
find_bot now returns each match's instructions, so the coordinator can
judge a worker by what it was told rather than by its name.
(The previous prompt is kept as a commented-out block at the bottom of the
file.)
create_workspace gives the coordinator a way to start a workspace with its shared context, and the tool list is shared, so a new id can be used by create_bot or add_bot_to_workspace in the same reply.
A coordinator's tasks now get create_workspace and update_workspace too: the research task that had the material could only report it, never write it into the workspace, so the coordinator promised an update it had no turn to make.
A workspace created from chat is pushed as server:workspace-created, from the tool and from the live relay, so the rail shows it without a reload.
Every bot now offers one concrete next step after answering in chat and
ends task reports with a suggested follow-up. The coordinator proposes
what comes next when a worker's report comes back.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
The coordinator had no tool to add a worker, so a request to create one
fell back to update_workspace and wrote a bot that did not exist into the
workspace context. create_bot now adds a worker with its name, role and
instructions and joins it to a workspace, and add_bot_to_workspace puts an
existing worker in one. Both are coordinator-only and chat-replies-only,
and createBot still enforces the crew-manager check.
The coordinator's prompts now say how a bot gets created, and that one
which does not exist is never written into workspace context.
pick-free-hue moves to utils so the tool can pick a hue without importing
from layouts.
- Schema: workspaces (+ workspace_bots, workspace_computers), containers,
computers, bot_computers, bots.memory, workspaces.system_prompt, and
bots_queue as a bun-sqlite isQueue table
- Main computer (and its container record) ensured with the coordinator on
signup, seed and /admin/bots; the coordinator's access to it is locked
- Effective computer access: direct grants plus workspace computers
- Full bot prompt: core instructions, workspace prompts, then memory;
bots can rewrite their memory and system prompt
- Queue helpers on the native BunSQLite.queue API, plus a handler that
heartbeats, serializes per computer, recovers after restarts, reports
lost jobs, supports cancelling and pushes outcomes over the WebSocket
- Enable SQLite foreign keys at startup so schema cascades fire
- Prune finished jobs daily
Co-Authored-By: Claude Opus 5.5 <[email protected]>
Local, password-only auth:
- No public pages; everything outside /admin and /auth redirects in
- First run (no users) sends every page to /auth/signup, which creates
the super admin (user #1) once and then locks
- Login is email/username + password; removed the emailed-code flow,
/auth/sso and email password reset
- Google login kept for existing accounts only, never creates them
- seed-super-admin now requires SEED_SUPER_ADMIN_PASSWORD
Bots-first admin:
- /admin and closed sections (people, logs, backups) redirect to
/admin/bots; only bots and settings are live (AdminSections)
- Removed the old admin layout; every /admin page uses the bots rail
- Coordinator bot created at signup/seed and by /admin/bots
(ensureCoordinatorBot), which redirects to its chat
- bots.system_prompt (markdown) with a default coordinator prompt
- seed-bots reuses the existing coordinator
Settings:
- Sub pages general (default), profile, change-password, listed in the
rail with a back link; unknown settings paths redirect to general
- Redesigned settings UI: pane header, grouped rows, sticky save bar
- General: System/Light/Dark theme, saved per device
Co-Authored-By: Claude Opus 5.5 <[email protected]>
tben
