- Claude Code as an engine: chats on a "claude-code/<alias>" model run through
the claude CLI (stream-json); tool approvals go through our permission
system. Sign in from the web UI (URL + pasted code), CLI version and update
from Settings; the Docker image contains the CLI.
- Small models (8k context) for side tasks: input is cut to the model's
context window; one-line chat status, "What does this do?" on approvals,
"Plan as automation" (job draft from a chat).
- Mobile: top bar no longer widens the page, image viewer (zoom, swipe, mark
up, use in message), jump to previous own message, message menu, time under
every message.
- Approvals: push actions (allow/reject), "always allow in this project"
(never for dangerous commands) with revoke.
- Per turn: changed files with diffs and rollback; project check command with
a green/red badge and "let the agent fix it".
- Colour tags for chats in the colours of the active theme.
- Project defaults for new chats, project page (timeline), offline queue.
Tested in a throwaway container with a mock model (8k small model): 26 API
checks passed (permissions, diffs, checks, defaults, job draft, side-task
budget, Claude Code status/login URL, unsigned-in chat).
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
- AgentConfig.reverse_tools (Settings -> Agents & commands) gives any mode
binary_info and decompile; the clean-room check of the tools applies to
craft only (ToolCtx.clean_room = clean room && craft).
- decompile: optional processor (Ghidra language id) and base_address for raw
images (BinaryLoader); separate cache per processor/address.
- Skill "reverse-engineering": identify, convert HEX, processor table for
common chips, decompile, explore, notes in analysis/.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
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>
- 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>
- 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>
- LICENSE (MIT), CHANGELOG for 0.1.0, README overhaul
- docker-compose.release.yml pulling the registry image
- Dockerfile cross-compiles the server with cargo-zigbuild for amd64 and arm64;
the terminal client is no longer built into the image
- Server, install script and settings point to a source install of the
terminal client when no prebuilt binaries are available (/info: cli_builds)
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>
- Personal API tokens (full/read scope, expiry, revoke) and CLI password login
- Cargo workspace: codecraft-core (types, providers, permission rules) shared by
server and the upcoming terminal client; server re-exports the old paths
- CLI server API: /cli/config, /cli/skill, /cli/tool (server MCP tools),
/llm/stream model gateway with budgets and usage per user
- Theme/language preferences mirrored to the server; personal memory endpoint
- Statistics: provider and mode tables stacked; CLI usage labelled
- cli/: work in progress (terminal client is being rewritten as a local TUI)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Web terminal (PTY over WebSocket, xterm.js, sandboxed, reattach with replay)
- Per-user git credentials and commit identity (credential store in the user's home)
- OpenSCAD tool (STL/3MF + preview renders, bounding box) and cad skill; 3D model card
- Craft phase inferred from tool activity when the agent does not report it
- Configurable review loop per mode (rounds, reviewer model, criteria)
- Delete config and Markdown agents from the agent editor
- Automations: cron-scheduled agents from Markdown job files, schedule tool, page
- change_directory tool (only on the user's request)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Sandbox (bubblewrap) for non-admin shell/git, MCP per-user rights, hard budgets and quotas,
login rate limiting, audit log and backups
- Ghidra headless decompilation (ARM64 natives built from source), binary_info tool,
clean room / deep workflow per session
- Recreate skill and commands for analysing and re-building old software
- File checkpoints with rewind/restore, background shells (bash_output, kill_shell)
- web_search tool (DuckDuckGo, SearXNG, Brave, Tavily)
- In-app dialogs and toasts instead of browser dialogs
- 15 base themes (trilium-themes palettes plus Nord, VS Code, GitHub, Catppuccin, One,
Dracula, Rose Pine, Everforest, Kanagawa) with light/dark/auto switcher and license notes
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
