ask_user puts up to six questions on one card (radios for one pick,
checkboxes for several, an optional typed Other) as a [question:ID] chip.
The user's answers are checked against the questions, stored in
bot_questions and sent to the bot as their chat message; Skip says so.
Offered in chat replies and user-started tasks, never in routines, hook
calls or chatroom sessions.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
Logs grew forever. A daily prune-logs cron now deletes entries older
than the app setting logs_keep_days (Settings > General, super admin;
default AppData.LogsKeepDays, 90), with an index on logs.created_at.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
The Files page and the conversation's files modal searched only on
Enter. Both now search by name or path a moment after the last
keystroke (useDebouncedValue, AppData.SearchDebounceMs), clearing shows
the whole list at once, and the modal drops an answer a newer request
overtook. The Files search box no longer locks while a folder loads.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
Every bot file was chunked into bot_file_chunks and embedded into
bot_file_vectors, and uploads kept their extracted text in
media.text_content, which together took most of the database. Bot
files are no longer indexed: bots find them by name or path with
list_files and read them with read_file, and search_files, ingest_file
and the files modal's re-read button are gone. Attachments keep no
text; a reply reads a document from the file. Only knowledgebase
documents keep text.
The schema drops both tables and the ingest columns. At boot,
dropStoredFileText removes what older versions stored (file jobs,
upload text) and vacuums once much of the database is free. The
media:prune-text script it replaces is removed.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
The sandbox ignores sandbox_execute_bash's timeout and runs every call in
one shared shell session, so a command that never ended (a network read
without a timeout, a prompt) kept running after the call gave up, and
every later command on that computer, from any run, timed out behind it.
Each command now runs in its own bash under coreutils timeout (at most
ComputerCommandMaxSeconds, below McpToolTimeoutMs), reading no input, and
says when it was stopped.
Replies' env list says where each key comes from and that workspace,
computer and install-wide envs reach every bot there, so bots stop
telling users a workspace's keys must be set per bot. The computer
prompt says installed programs may be gone after a restart. An empty
open-only task list says closed tasks aren't shown, and update_task says
when a status was already set.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
Job steps (bots_queue_updates) only feed the live working row, so the
new clear-job-steps cron deletes them shortly after a job ends, however
it ended, keeping their count on bots_queue.steps for the message
details. Not done the moment a job ends: the live relay would miss the
last ones.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
A worker asks for another bot's help with ask_crew. The coordinator
reads the request, asks the right bot (in a workspace, only its
members), and sends the answer back into the asking bot's
conversation, waking it. Each exchange is kept as a read-only
chatroom: listed in the main rail after the workspaces, or in the
workspace's rail for requests made there, with live status rows for
each bot while it's open and a Stop button.
Room sessions are hidden from every conversation list, other bots'
words reach the model fenced as data, and turns, nesting and open
rooms are capped. Closed rooms are pruned after a retention period
and past a cap per place (Settings > General).
Co-Authored-By: Claude Opus 5.5 <[email protected]>
A managed Chrome policy, written as root into each running computer's
container on provision and every sync-computers run, installs the
default extensions (normal_installed: can be turned off, not removed).
Existing computers get it without being recreated.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
Bots can now show a concept as a visual: create_graphic (with
update_graphic, read_graphic and list_graphics, on every run, no computer
needed) stores one HTML document in bot_graphics, per user like the
conversation, and the chat renders its [graphic:ID] ref as an inline card
sized to fit, with a large view and a page of its own (no rail).
Graphic HTML is treated as hostile: it is only served at /graphics/<id>
with a CSP sandbox allowing scripts under an origin of its own and no
network, loading only the vendored Chart.js and Mermaid from
/graphics-lib/. The document carries the app's theme vars and scrollbars,
reports its height to the thread, and a frame that navigates away is
closed.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
Knowledgebases give bots RAG over documents, scoped like extensions: to
particular bots, to a workspace, or to every bot, with their own button
beside Tools in the composer. Documents are chunked and embedded by the
file-ingest worker with the install's embedding model, which is now an
install-wide setting rather than a per-bot one.
- Word search runs on an FTS5 index ranked by BM25, with a scored LIKE
fallback for scripts written without spaces.
- Changing the embedding model re-indexes documents automatically.
- Ingest jobs wait without spending attempts while every embedding model
rests, fail at once on errors retrying can't fix, and keep passages
searchable by words when the model refuses.
- Settings > Knowledgebases shows each knowledgebase's and document's
index state: spinner, warning, grey check (words only) or green check.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
- Bots get continue_in_new_session: the bot writes a title and summary,
the session closes for good (read-only) and the new one opens with the
summary as a "Carried over from the last session" message that links
back to the old session.
- Continue in new session (conversation menu, sessions modal) and the
automatic rollover at the session length do the same; New session now
starts a fresh, unlinked session.
- Session length is an app setting in Settings > General.
- ?session_id= opens a session; a carried-over one shows a bar linking to
where the conversation went on instead of the composer.
- The thread can open the previous session above the current one (shown
only, never in the prompt), and replies get search_past_sessions and
read_past_session.
- Sessions are named from their opening messages, not their latest, and
a carried summary is labelled as the earlier session's.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
A hook call used to record only how it was taken; its run's answer went
to the chat alone and was lost to the call once the job was pruned. Now
`bot_hook_events` keeps `response`, `response_message_id` and
`responded_at`, written on every call a run took in when that run ends
(completed, failed, lost, stopped or cancelled) by
`recordHookCallResponse` in the job helpers, and calls turn done or
failed. The Calls view searches what calls sent and what runs answered,
filters by status and pages; Show all loads one call whole. Bots get
`search_hook_calls` and `read_hook_call` for their own hooks (never in a
hook call's own run), with payloads always marked as outside data.
Calls are kept for the app setting `hook_events_keep_days` (Settings >
General, default now 30 days). The caller still only gets 202 Queued.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
A new personal env scope (paradigm user: one user's secret for one bot)
beats every other scope, reaches only that user's runs of that bot, and
is redacted like any secret. Bots take secrets in with request_secret,
which puts a [secret-request:ID] card in the chat: the user types the
value into a masked input there, never into a message, and the bot is
told only the key. Bots show secrets with capture_secret (a task's
computer tool that saves a file or a command's output straight to a
personal env, then redacts it from the rest of the run) and show_secret
(an env by key): both give a [secret:ID] chip whose Reveal and Copy fetch
the value on click, for its own user (personal) or a super admin
(anything else), logged by key. Values never go into messages, page
props, history, Copy chat or logs. Users manage their own secrets on
Settings > Secrets; the Environment page lists everyone's, remove only.
Deleting a bot or user removes its personal secrets, and SecretsNote
tells bots never to ask for or print secrets in chat.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
Each computer's Chrome profile now lives on the data volume
(DATA_DIR/computer-browsers/<id>, mounted at ~/.cobble-browser) and
Chrome is pointed at it with --user-data-dir. The sandbox image resets
its own profile's preferences to session-only cookies on every boot,
which signed every site out whenever Chrome exited. New profiles are
seeded with the image's preferences minus that rule, stale Singleton
links are removed before each provision, and existing computers are
recreated once (skipped while a job runs on them).
Co-Authored-By: Claude Opus 5.5 <[email protected]>
A bot hook (bot_hooks) is a secret URL, POST /api/hooks/<token>, whose
calls queue the hook's brief plus the raw body as a task, per user and
bot like a routine. Only the token's hash is kept (shown once, rotatable);
an optional HMAC-SHA256 signing secret is stored encrypted. Calls are
rate limited per address and per hook, recorded in bot_hook_events
(pruned daily), deduplicated by delivery id, and a call while the last
run still waits joins its brief instead of queueing another. The payload
is fenced data and HookRunNote tells the bot never to take instructions
from it; failed runs retry like routines.
A hook can instead watch a computer's browser notifications: the app
installs a small watcher that owns org.freedesktop.Notifications on the
sandbox's session bus, so Chrome hands it every notification (it only
looks for that service at start-up, so Chrome is restarted once, never
mid-task), and it posts each one to its hooks, optionally filtered.
Computers reach the app at COMPUTER_APP_URL or the app container's name.
Users make hooks in the conversation's Hooks modal and manage them all
on /admin/routines; bots never create or change hooks.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
The longest runbook a skill may save and how much of it load_skill hands
back are now set on Settings > General (skill_body_max_chars,
skill_body_shown_chars), defaulting to AppData.SkillBodyMaxChars and
SkillBodyShownChars. Saving, confirming and proposing a skill check the
install's limit; a skill saved before it was lowered can still be toggled.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
A data archive or restore ran inside its request, which sent nothing
until tar finished: Bun closes a silent socket after 10s (its default
idleTimeout in production) and a proxy cuts it at about 100s, so the
page showed a network error while the archive kept going, and a retry
said another backup was already running.
The routes now start the run (startDataBackupRun, refused while the
backup lock is held) and answer at once. The page follows it by polling
api/admin/backups/data-status: an archive reloads once written, a
restore once the status comes from a new process after its restart,
and a failure shows its error. A run in progress survives a reload.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
Computers now mount only /home/gem/workspace from DATA_DIR/computers/<id>,
so only the workspace persists and goes into the data archive. An older
computer's whole home is moved aside to <id>-home-<ts> (kept, never
archived) and its container recreated once by sync-computers.
Each run works in bots/<bot>/users/<user> (also its cwd and HOME), with
bots/<bot> for work every user shares and workspaces/<id> shared by a
workspace's bots; the coordinator reaches the whole workspace. Computer
tools are gated by withComputerDirs: bash and code start there, file tool
paths and file: URLs outside the run's folders are refused, and so is sudo.
search_computers, import_file and script tools start there too.
The files browser shows members only the bots' folders they reach, their
own user folder in each and their workspaces', with names on the id folders.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
- Coordinator tools in its own chat (super admin only): list_extensions,
set_extension_access, delete_extension, and update_skill /
update_mcp_server / update_custom_tool for what can't change where
anything is sent (on/off, names, arguments, left-out tools)
- Adding a skill, MCP server or tool, or changing a skill's words, a
server's URL or headers or a tool's kind or config, goes through
propose_skill / propose_mcp_server / propose_custom_tool: stored in
extension_proposals with the bot's background check, shown as a
[proposal:ID] chip that opens a card with Confirm and Reject
- The card's facts are worked out by the app from what Confirm saves: the
host, every {{env.KEY}} and whether it's saved, the config; for a skill
its links, hosts, tool names, mentions of secrets and a diff against
the saved runbook
- Confirming decides once and checks again; a server or tool missing a key
is saved switched off, and the outcome is posted to the bot in chat
- Never from a bot: stdio servers, a URL whose host a template decides,
envs in a prompt tool, a key's value
Co-Authored-By: Claude Opus 5.5 <[email protected]>
A reply read the session once at the start, so a message sent while it
ran was never seen, and the follow-up reply queued for it then finished
silently: the message was saved before the reply, so the thread ended
with the bot. Those messages went unanswered.
The text loop now reads new user messages after every round of tools and
before an answer goes out, and the bot decides from what each one means
whether it changes the work (folded in, or the unsent answer redrafted)
or is a separate request, which it acknowledges at once with the new
send_message tool and does after the current work. Messages sent that
way are marked interim, so the thinking row stays up while the bot
works. A reply job records the newest user message it read, and a queued
reply only stays silent when a finished reply already read everything.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
Every bot message gets an info button that opens its details: the
provider and model behind it, tokens and cost, the job that ran it, each
model used and every call in order. Each model call now records how it
was made in token_usages.settings (generation settings sent, whose
settings they were, pinned or automatic model, fallbacks), shown per
model in the modal.
Live replies now carry their token usage, from the job's push and the
live relay alike, so it shows without a reload.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
The two limits were compiled in: a task run stopped at
AppData.HarnessMaxToolSteps (200) and a chat reply at
AppData.BotReplyMaxToolSteps (8), so an install that needed a longer task
had to rebuild.
Both are now `app_settings` rows (`harness_max_tool_steps` and
`bot_reply_max_tool_steps`), read at the two loop call sites through
grabHarnessMaxToolSteps and grabReplyMaxToolSteps, and edited by the super
admin on Settings > General beside the prompt appendix. Zero clears a
limit back to the code default, like the bot file quota.
readStepLimit keeps the saved number only when it is a whole number of at
least 1 and no more than AppData.BotStepLimitMax (1000), so a blank, a
zero or a typo falls back instead of stopping every run before its first
turn, and a huge number still ends in the wrap-up report.
runTextLoop keeps AppData.HarnessMaxToolSteps as its default, so it stays
free of database reads and its tests run as they did.
Nothing anywhere recorded what a model call cost: the harness used a
provider's usage numbers only to decide whether a turn had finished, then
dropped them. So a reply could not say what it took to make, one model
could not be compared with another on price, and there was no way to ask
what a day, a week or a month of the crew's work came to.
- `token_usages` records one row per call: user, bot, workspace, session,
job and message, the harness, the provider and model that actually
answered, the prompt and completion counts, and the cost when the
provider reports one.
- `harness-usage-scope.ts` carries those ids in an AsyncLocalStorage
scope that `run-bot-job.ts` enters once, so a run's turns, its session
summary, its transcriptions, images and embeddings are all attributed
without threading ids through every harness function. Nested runs merge
rather than replace, and a null genuinely clears a field (a bot's own
chat has no workspace).
- Work with no run behind it is charged to its owner instead:
`run-with-fallback-scope.ts` reaches the workspace's creator else the
bot's, and deliberately does not override a real run, so an ingest a
bot asked for is not misattributed to the bot's owner.
- All six harnesses record through `withCandidates`'s `on_success`.
Recording never throws: a model that answered must not lose its answer
to a failed insert.
- A job's calls land before its message exists, so `complete-bot-job.ts`
back-fills `message_id` once the message is inserted.
- The message's actions row shows what it cost, beside the timestamp and
the play button, with the breakdown in its title.
- `/admin/usage` totals the install's spending for 7, 30 or 90 days: the
total against the previous period, a day-by-day chart, a split per kind
of call, and a table per model with the price per thousand tokens
worked out from cost and tokens, which is what makes two models
comparable. Crew managers only, since it is the whole install's work
rather than one user's conversation. It sits with Routines and Activity
in the user popover rather than under Settings, because it is a record
of what happened, not something to configure.
Days are grouped in local time (`date(created_at / 1000, 'unixepoch',
'localtime')`), matching the local midnights the window builds and the
`YYYY-MM-DD` buckets it looks up. Grouping by the bare UTC day put a late
evening's calls under a name no bucket carried, so they vanished and the
chart's total silently disagreed with the totals card; a test pins it.
`canSeeRailItem` now decides who sees a popover or rail entry. The two
each filtered with their own inline rule and only one understood
`can_view`, so a gated page could be offered in the popover to everyone.
A new super admin settings page, /admin/settings/database, lists every
table with its record count and size, and one page of the open table's
records newest key first. Values are cut inside SQL (400 characters, with
a flag saying so) and a record opens whole in a modal, so a table of long
texts reads without shipping it all. A search matches every column's
text, word by word or as a phrase, which is the one thing that also works
on a virtual table. Nothing in it writes: the catalog, the records and
the single record are all reads, GET only.
`text_content` is an extracted-text cache, but nothing stopped it from
holding a dump of bytes:
- `fileToText` ended its switch with `default: return buffer.toString("utf-8")`
and defaulted a missing extension to "txt", so any binary was decoded.
- Both extraction callers gated on `media_type == "document"`, and
`attachmentFileKind` classes everything non-image/audio/video as a
document: an SVG, a zip, a spreadsheet, a .bin.
- Nothing capped the length, so a 20 MB attachment could leave 20 MB of
text in the database.
- `storeChatAttachments` copied the text onto a second `media` row, and
`SELECT m.*` pulled the column into page props and API responses.
On a real install an SVG held 6852 characters of markup and a
`.designcraft` file held 142 KB of raw bytes.
Changes:
- `file-to-text.ts` lists the text extensions explicitly and returns
undefined for anything else; no extension is no text.
- `can-extract-text.ts` is the one allowlist (reusing
`BotTextFileExtensions`), used by both upload routes and by
`uploadAndRecordMedia`; `extension-of.ts` is shared with the storage
catalog instead of duplicated.
- `BotAttachmentTextStoreMaxChars` (200k) caps the column via
`cap-text-content.ts`.
- `store-chat-attachments.ts` no longer copies the text; ingestion
re-reads the bytes once.
- `media-columns.ts` selects every media column but `text_content`, which
now has to be asked for (`grab-messages-media`'s reply path and
ingestion do); the media CRUD routes sanitize rows they write.
- `ingest-bot-file.ts` decides on size alone, since a cached slice made
an oversized file look already read.
- `bun run media:prune-text` cleans rows that were already stored
(rerunnable, with a VACUUM hint).
Verified on the dev database: both bad rows cleared (146 KB), rerun
reports nothing to do.
A skill is a runbook: a name, a unique slug, a one-line description of when
it applies, and the markdown body. A run only ever sees the slug and
description (one load_skill tool carries them), and reads the whole body
only when it calls the tool, so a long runbook costs nothing until needed.
Skills are the third extension kind beside MCP servers and custom tools, on
the same botExtensionsSql path, so per-bot, per-workspace and all-bots
grants work the same way, and attachDefaultExtensions hands an every-bot
skill to new bots. load_skill is a reserved tool name, so a custom tool
cannot shadow it, and a built-in wins a clash.
Managed on Settings > Skills; ExtensionRow links each kind to its own page
and a skill never reports a failure, since nothing connects or runs.
Bot and user messages get a quiet copy button under them: the copy icon becomes a check for a moment after it copies the message's text as stored, markdown and refs included. A message still on its way to the server can be copied too, though reply and reactions wait for its id. The async clipboard API is used where it exists and a hidden textarea where a plain HTTP install has none.
`/admin/bots` sent the super admin to the coordinator and everyone else to
their latest bot, which lost the thread each time the tab was reopened. The
conversation pages now record where the browser is in two HttpOnly cookies
(`cobble_last_visited_bot_id`, `..._workspace_id`, a year, `Secure` only over
HTTPS), and the landing page opens that conversation again, in its workspace
when it was one.
A stale cookie can't loop: `grabReachableConversation` re-checks it with
`grabUserConversation`, the gate the conversation pages use, so a revoked
grant, a deleted bot or an archived workspace falls back to the coordinator
(super admin) or the latest bot, first workspace, empty page. Signing out
clears both cookies so the next user on that browser doesn't land in the
previous one's conversation.
Settings > Backups gains a whole-data archive beside the database
snapshots, and both lists now fully work from the page.
- Data archives: `write-data-backup-archive.ts` tars all of DATA_DIR into
BACKUP_ARCHIVE_DIR as cobble-data-<epoch-ms>.tar.gz, every entry under one
root folder named after the archive, writing a .part name and renaming on
success so a cut-off run is never listed. The newest
AppData.DataBackupsKept are kept; db/.backups is left as it is.
- Restore: `restore-data-backup.ts` extracts to a temp dir, requires one
root folder holding a db folder, takes a safety archive first, then
replaces DATA_DIR (the database snapshots included) and `restart-app.ts`
restarts the process through the docker socket, since the open SQLite
handle points at the replaced file.
- Upload and restore: a modal over each list (database file or data
archive), replacing the old /admin/settings/backups/restore page.
- Delete for both kinds, icon-only row actions shared through
RowIconButton, and restore on every row.
- One backup or restore of either kind at a time (with-backup-run-lock).
- BACKUP_ARCHIVE_DIR is a start-up path (ProcessOnlyEnvKeys); the installer
mounts $COBBLE_HOME/backups-archives at /backups-archives and recreates a
container that lacks it. The image installs tar and gzip.
The rail header now sits in the standard 64px row with a hairline under
it, matching the pane headers, and shows the full logo off the chat
pages instead of the bare stone. A back button joins the conversation
and settings headers (workspace pages only for the conversation). The
rail's own back link and the dividers around it are switched off for now.
Also renames the bot and workspace Delete group to Danger Zone, lifts the
step budget to 50, and lets Logo render without its home link.
import_file sent a computer's bytes back with base64 over /v1/shell/exec,
whose stdout is capped at 30,047 characters. Every import was therefore
cut at 22,528 bytes and saved anyway, with the tool reporting success: a
1.12 MiB archive became a 22 KB file that would not open, and a crawler's
crawl.json lost half its pages.
The bytes now come from the sandbox's streaming GET /v1/file/download.
The size is read first so nothing over BotFileImportMaxBytes is
transferred, the download asks for change_policy=abort so a file that
changes mid-send is refused rather than half-saved, and the received
length is checked against the size read, so a cut-short transfer fails
loudly. Folders go the same way, as a gzipped tar unpacked into one row
per file.
Bots also name a path as [path:volume:owner:path] now, so what a bot
leaves on a computer is a link into the files browser instead of text.
Bots and workspaces each keep a list of work tracked until it's done, and
the bots move it along themselves as they work.
- tasks (one collection per bot or per workspace), task_notes (the
progress log) and task_media (a deliverable or a reference file, its
bytes a private media row served at /media/private/<id>)
- statuses todo/doing/blocked/done/cancelled, with blocked_reason while
only the user can unblock it
- visibility as SQL in src/utils/task-access: a user's own bots and
workspaces, a run's own list plus its workspaces, everything for the
coordinator; every tool and endpoint resolves through it
- list_tasks, create_task and update_task on every run, so a chat reply,
a task and a routine all read the list, log progress and file what they
produced
- TasksNote on every run and TaskReminderNote in chat, so a greeting or a
proposed next step brings pending work up in one measured line
- tasks group on the workspace dashboard and a tasks modal in the
conversation header, sharing one form, row and detail panel
- a bot's or workspace's own chat uploads are read before the delete so
none are stranded; bot files keep their folder
Also corrects the README's RAM guidance and table alignment.
The app never terminates TLS: a reverse proxy or tunnel does, and
isSecureRequest still reads X-Forwarded-Proto so cookies stay Secure.
Removes the cert generator, TLS resolution and HTTP redirect, the
local CA download, and the TLS envs, and trims the installer, Dockerfile
health check and docs to match. Also softens the composer's loading row.
Bot and workspace lists in page props leave out instructions, memory and
workspace context, and carry the last message as a short preview. The
header avatar's edit form loads the bot's instructions when it opens.
The conversation renders its latest 30 messages and loads older ones as
the thread scrolls to its top.
Also: the composer shows a placeholder until its editor loads, and
`bun start` no longer builds first.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
In production, a page request without the running build's cookie gets a
small loading page instead of the app. It downloads every file in
.bunext/public (listed at /build-info.json) into that build's cache,
checks they are all there, hands over to a new service worker waiting
behind an older one, sets the cookie and reloads. The service worker
then serves the app's code from the cache, so later visits load it from
the device.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
- Cache the model catalog once per user and each conversation's setting
separately; clear both on logout and after model saves
- Compress hashed assets asynchronously with a byte budget and set Vary
- Memoize message parsing and throttle selection reads
- Debounce draft writes to localStorage
- Keep the composer editor on the page and focused, as before
- Add a bundle budget check and run it in CI
- Show a loading block while sessions load and a workspace avatar in the
mobile conversation header
- Compress responses: page scripts and styles once (brotli or gzip, in
memory) and cached immutable; pages and API JSON gzipped as they stream
- Service worker serves content-named assets cache-first
- Load the models modal's data when it opens (cached in localStorage)
instead of shipping the model catalog in every conversation page
- Lazy-load the Tiptap composer and memoize thread messages
- Import lucide icons directly; twui 0.1.4 drops by-name icons from Button
- bun run start builds the pages minified before serving
Co-Authored-By: Claude Opus 5.5 <[email protected]>
The installer generates a CA and a 397-day certificate into
$COBBLE_HOME/certs (in the app image, with the host's addresses), mounts
the certificate, key and CA into the container and serves TLS from Bun on
the published port. --no-https opts out; --https-cert/--https-key use a
real certificate, --https-host adds names and --https-regen replaces the
CA. The installer and the image health check use curl -k when TLS is on.
The CA is served at /ca.crt and as an iOS/macOS profile at
/ca.mobileconfig for one-tap install. Development picks up certs/
automatically, `bun run dev:phone` generates and starts, and a plain-HTTP
listener on PORT + 1 redirects to HTTPS. Port sharing is off, so a stale
dev server fails instead of silently answering on the same port.
Scheduled runs are pre-approved: they carry out their brief instead of
drafting for confirmation. A run that can't do its brief calls
report_run_failed and is retried 5 and 10 minutes later; only then does
the user get one "failed after N tries" message, and the routine keeps
why in last_error.
Every reply and task now gets ActionCheckNote: look for an existing
record before creating one, and verify an action took effect before
saying it's done. Memory and instructions saves are read back, and
create_bot, create_schedule, start_task and delegate_task refuse
duplicates.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
The composer now writes markdown with bold, italic, strike, code,
links, quotes and lists, from shortcuts, markdown typing or a bubble
over the selection. @ mentions a bot and # a workspace, shown as chips
and saved as [bot:ID] / [workspace:ID]. Text selected in a message can
be quoted into the composer. User messages render as markdown, and
replies tell the bot who and what the user mentioned.
Adds an ESM stand-in for use-sync-external-store, since bunext keeps
React external in page bundles and the CommonJS original requires it.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
The Speech section of every model settings form now has "Hear a
sample", which streams a short sentence (AppData.VoicePreviewText) in
the form's model and voice before they're saved, through
GET api/admin/harness/preview-voice (super admins and admins, that
model only via grabModelCandidate). pickVoice is shared with
speakText, and explainAudioError reads why a streamed player failed
for both read-aloud and the sample.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
- A mic in the composer records, transcribes with the bot's
transcription model (api/admin/bots/transcribe) and writes the text
into the input at the cursor to edit before sending. Escape cancels;
recordings aren't stored.
- Every bot message has a read-aloud button that plays
GET api/admin/bots/speak-message, streamed from the provider as the
audio is made, so it starts in a couple of seconds. One message plays
at a time; only the user's own sessions can be read.
- Both buttons stay visible but disabled while the bot has no model for
them (bot_voice page prop).
- Transcription and speech no longer pick free models automatically:
they're not available until a model is picked, and Settings says so.
Transcription lists speech-to-text models only, so the chat-model
transcript path and its missing-audio check are gone.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
Sessions no longer take their title from the first message: once the first exchange is sent, the text model writes the title and summary, which the rail and sessions list show. The summary records how many messages it covers so a stale one is rewritten before it is carried into the next session.
The sessions hook now reloads on live message and session events, so a session started by the first message, a rollover or another tab appears without a reload. New sessions are pushed as server:bot-session, both from the process that changed them and through the live relay.
Show the latest five sessions under the active bot, with All sessions opening the existing modal once there are more. Share the session modal, row and hook outside the conversation page, and mark the current session with a muted row.
tbenandClaude Opus 5.5