Context window
- Requests asked for the model's full max_output, but providers count
input + output against the window: long chats with large-output models
(DeepSeek V4.1 Flash, 384k) failed with "input too long" before automatic
compaction (85 %) kicked in. max_tokens is now what the window leaves
(estimated input = last usage + messages since), the chat is compacted when
less than 32k would remain for an answer, and a context-overflow error
compacts and retries once.
- ModelConfig.max_input (catalogue limit.input, editable in the provider
settings) lowers the compaction threshold for models with an input limit.
Enforced reviews (modes with refine.rounds > 0, refine.after_todos default on)
- Every todo marked completed is reviewed against the work since the last
review; with findings it is reopened and the feedback goes to the agent
(max. rounds per todo). Passed reviews leave a visible note.
- Ending the turn with open todos sends the agent back to work while it makes
progress (max. 10 reminders in a row without progress); such modes may take
up to 2,000 steps per turn. Reaching the step limit is reported.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
User messages are rendered with the same Markdown component as the model's
answers; single line breaks are kept (hard breaks outside code blocks), so
plain multi-line messages look as before. The eye button next to the text
field shows the formatted message before sending. The text sent to the model
is unchanged.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Automations
- Job files hold only the instructions; name, schedule, mode, model, approval
mode and time limit are settings in the database (jobs.settings). Existing
files are adopted on start-up (frontmatter into the database and removed from
the file); plain Markdown files registered later get default settings and stay
switched off until scheduled.
- New automation: name, project and a starting point (blank example structure or
a template) create .codecraft/jobs/<name>.md and open the editor: settings with
a graphical cron builder (next runs in server time via /jobs/schedule), the
instructions in the Markdown editor and an assistant chat
(POST /jobs/{id}/assistant) whose model edits the file; the editor reloads it
after each turn and warns about conflicts with unsaved edits.
- The schedule tool writes prompt-only files with settings.
Chat list
- Folders and projects keep a user-defined order and can be pinned (drag and
drop, or the group's menu), stored per user via /account/sidebar. A new
message moves the chat to the top of its group, no longer the project itself.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Automations: the approval mode is a selection in the list; PATCH /jobs/{id}
writes permission_mode into the job file's frontmatter (rest of the file
unchanged, invalid modes rejected). "Allow everything" lets nightly runs work
without waiting for approvals via Telegram until the timeout.
- Session.telegram_quiet: approvals and questions of a chat (and its subagents)
are not sent to Telegram; the chat open in Telegram always reports. Toggle in
the chat's ⋯ menu when a bot is paired. New chats from the web UI and
automation runs start quiet; chats started from Telegram and existing chats
keep reporting.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Installed apps checked their service worker at /sw-<old build>.js. That file no
longer exists after an update and the static fallback answered with index.html,
so the update check failed and the old worker kept serving the previous app
shell. The old frontend crashed on the new image references (base64Size of a
missing `data`), leaving a blank page on phones. Old service worker URLs now get
the clean-up worker (/sw.js), which unregisters and reloads; missing scripts and
styles answer 404 instead of HTML.
- Task list above the composer folds to one line (progress, current task),
remembered per device.
- max-height: 560px layout (square phones such as the Clicks Communicator,
landscape): tighter top bar, composer and new-chat wizard.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Images of messages (pasted images, screenshots, generated images) were base64
inside the message JSON, so opening a chat downloaded all of them at once
(66 MB for a chat with 120 screenshots). They now live in a `blobs` table,
addressed by SHA-256; messages keep a reference (blob, size). The UI loads
them from /api/blobs/<hash> lazily with an immutable cache header, the runner
fills the bytes in before model requests, JSON exports stay self-contained.
- Store::add_message moves inline images out; large opaque PNGs become JPEG
(q85) when smaller. Older chats are converted once at start-up in the
background, unused images are removed (also after deleting a chat) and the
database is vacuumed when that frees 32 MB or more.
- Responses are compressed with gzip/brotli (not images, SSE streams or
binary downloads).
Example (copy of production): chat load 66 MB -> 1.5 MB (370 KB brotli),
database 90 MB -> 27 MB.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Set GIT_AUTHOR_*/GIT_COMMITTER_* from Settings → Account → Git (also inside the
sandbox), so a repository's own user.name/user.email no longer wins; tell agents
not to change the git identity.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Up to three chats side by side (#/s/a+b+c), "Open beside" in the sidebar menu
- File manager tabs of a chat stored per user on the server (/sessions/{id}/tabs)
- Personal modes for every user (Settings → My modes, /account/modes)
- Budget meters (total, provider, images, opencode Go windows) with push warnings
for admins at the warning share and 100 %, shown in the status overlay
- scripts/move-server.sh: move to another Docker host with bind mounts (Unraid);
scripts/smoke-test.sh
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Terminals and file managers as tabs of a chat; chat terminals keep running on
the server (no idle timeout) and re-attach from any device
- "Just chat" in New session and a built-in chat mode with a lean prompt and only
web tools; custom modes with kind (coding/conversation), read-only and tool picker
- Mode selector as a dropdown
- The chat shows running compactions (automatic: tokens and share of the limit)
and labels summaries
- Docker image builds and serves the terminal client binaries again
- Fix: atomic session updates; background title/usage writes no longer undo each
other (auto compaction triggered one turn late)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Fetch prices for opencode (Zen and Go) incl. limits, image input, reasoning,
long-context tiers and peak-hour/date factors; costs apply them per request
- Record the cost opencode reports per response; track Go allowance in 5h/7d/month
windows against a provider plan limit (budget table, status overlay)
- Settings → Config file: move values of ${NAME} references into the config
- Examples, presets and forms keep keys in the config instead of .env
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Sidebar: three status LEDs (server, models, MCP) with an overview popover (/api/status)
- Images: preview stage, purpose-based model choice and reference images
(Nano Banana Pro edit refines the chosen preview)
- Settings: restore a stored or uploaded backup (staged, applied on restart)
- Provider form: test connection; saving or reloading re-checks the status at once
- opencode Zen/Go: send x-opencode-session with a stable id per conversation
- Releases are named vYYYYMM-NNNNN; scripts/release.sh numbers, tags, builds and publishes
- Fix: backups made in the same second no longer overwrite each other
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Daily backups (database + config) into <data_dir>/backups, keep N,
optional upload to any S3-compatible bucket (SigV4, bucket pruning);
settings panel with run-now, list and download
- Daily cost summary push at 20:00 (opt-in per user, preview button)
- Automations from templates (dependency check, security review, test
health, daily summary, TODO report, docs freshness) via POST /jobs/create
- browser tool: headless Chromium over CDP – click, type, keys, waits,
JavaScript, navigation, screenshots, console errors; requests to private
network addresses are blocked (sub-resources and redirects included)
- Secrets masked in the config view: S3 secret key, metrics token
- Replace the remaining text arrows/refresh glyphs with SVG icons
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- PWA share target: shared text/links start a new chat or go into a
recent session (chooser dialog)
- Prompt templates (personal + global for admins) with {{placeholders}}
that are asked for on insert; managed under Settings → Templates
- Ctrl/Cmd+K command palette; Alt+N new session, Alt+Up/Down switch
sessions, Ctrl+, settings
- Sessions can be pinned, archived and filed into folders; the list can
be grouped by date or by project, groups are collapsible
- Fix: the "What's new" dialog was never shown to signed-in users
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- codecraft: full-screen terminal client (ratatui) – local tools and files,
models via the CodeCraft server gateway or own providers (standalone with a
guided setup), slash commands, @files, permission dialogs, resume, update
- Static Linux CLI builds (x86_64/aarch64, cargo-zigbuild) served by the
server: /cli/install.sh and /cli/download/<target>
- Project memory (remember tool, .codecraft/memory.md) and personal memory
- Model fallback when a host is unreachable or a budget is used up
- Version/commit in UI and health, daily release check, "What's new" dialog
- PWA: install button, maskable icon, manifest id and screenshots
- Case-insensitive detection of connection errors for retries
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Richard ZinkandClaude Opus 5.5
Richard Zink