* fix: don't overlap thinking banner over conversation * feat: support message queue and add attention indicator * fix(shell): use c to copy for claude * fix: strip timestamp tags from cursor * fix: select project when loading session from direct URL * feat: support attached images for all providers * feat(opencode): support permission options * fix: resolve source control and chat UX bugs - make staging real in the git panel: new /stage and /unstage endpoints, /status now reports the actual index via porcelain -z (handles renames, conflicts, and paths with spaces), and Stage/Unstage All run real git commands instead of toggling client-side state - add branch search to the header dropdown and Branches tab - persist the chosen permission mode per provider so a brand-new chat keeps it once the session id arrives, instead of reverting to default - replace cmdk's fuzzy model search with strict token matching so "chatgpt" no longer surfaces unrelated models - unit tests for the git status parser * feat(git): commit graph in history view and cross-spawn everywhere - render a VSCode-style commit graph in the source control history: lane-assignment algorithm, SVG strip with colored rails, merge and branch curves, commit dots, and branch/tag badges per commit - /commits returns parents and ref decorations across all branches (--branches --remotes --tags --topo-order) using unit-separator fields so pipes in commit subjects can't break parsing - collect stats via a single --shortstat pass instead of one `git show --stat` call per commit; raise the history limit to 50 - replace child_process spawn with cross-spawn in all runtimes, routes, and services: it resolves .cmd shims and PATHEXT on Windows (fixing taskmaster's npx invocations) and delegates to native spawn elsewhere, removing the per-file win32 ternaries - unit tests for the log parser and lane assignment * fix: remove gemini support since google discontinued it * fix: address code review findings - validate chat image attachments server-side: only files inside the ~/.cloudcli/assets upload store may reach provider file reads - harden asset serving with nosniff and attachment disposition for SVGs to prevent stored XSS - show the timestamp on image-only user messages - serialize git stage/unstage calls and defer the status re-sync so rapid toggles can't interleave or flicker - use a literal hex fallback for commit ref badges (alpha suffix on a var() string produced invalid CSS) - stop binding a URL session to a guening project instead - add the missing attentionRequiredIndicator key to all sidebar locales - clean up dangling conjunctions left the de/ru/tr/ja/zh-CN/zh-TW READMEs * fix: address code scanning findings - enforce a second image trust boundary in the provider builders: buildClaudeUserContent/buildCodexInputItems only accept files inside the upload store or the run's working directory (CodeQL path injection) - drop an always-true selectedProject check in handleSubmit - remove the unused resume option from spawnCursor * fix: use CodeQL-recognized containment check for image reads Replace the path.relative guard in isPathInsideDirectory with the resolve + startsWith(root + sep) idiom so the path-injection barrier is visible to code scanning; behavior is unchanged. * fix(security): canonicalize Claude image attachment reads Resolve image attachment paths with realpath before reading so symlinks inside allowed roots cannot escape to arbitrary files. Preserve support for symlinked project/upload roots and add focused coverage for both cases. * fix: show agent subtask * fix(sessions): title app-created sessions from the first user message App-created sessions (started by sending a message from cloudcli) were titled with placeholder names — "Untitled Codex Session" from the disk indexer and, briefly, "New session" from the empty canonical upsert — before a later sync finally settled on the right text, causing the sidebar title to flicker. - Codex/OpenCode synchronizers now title app-created sessions (distinct app id mapped to a provider id) from the first user message, while sessions found purely by indexing keep their existing setup. Claude keeps its AI-generated titles; Cursor already used the first message. - Decode OpenCode's JSON-string-literal prompts so titles no longer surface wrapped in quotes; hoist unwrapJsonStringLiteral into shared/utils since it's now used by both the reader and synchronizer. - Guard the sidebar upsert merge so an empty summary can never blank out a title that is already set. - Add codex/opencode synchronizer tests for the app-created vs indexed naming paths. * fix(chat): make message queuing reliable across sessions and turn boundaries Queued messages had four related defects: - A queued message flashed and then vanished at flush time: concurrent transcript refreshes (the `complete` handler racing the watcher-triggered update) could resolve out of order, letting a stale response overwrite newer server messages after the optimistic row was pruned. Session slots now carry a monotonic fetch ticket and discard stale fetch/refresh/ fetchMore responses. - Switching sessions flushed the previous session's queued draft into the newly viewed one (sending it with the wrong provider's settings, e.g. a Claude model into a Codex session). The composer flush is now scoped to its session, and a draft restored into an idle session sends after a short grace period so a live-run ack can cancel it. - The thinking banner never appeared for a queued turn: the chat handler's session-keyed completeRun safety net could fire after a queued message had already started the session's next run, emitting a spurious `complete` that killed it. The safety net is now scoped to its own run via completeRunIfCurrent (with a regression test). - Queued messages only sent while their session was being viewed. Drafts now persist their send options (model, effort, permissions) at queue time, and a new app-level useQueuedMessageAutoSend hook dispatches a non-viewed session's queued message as soon as its run completes, using the storage key as the claim ticket to prevent double sends.
Sandboxed coding agents with a web & mobile IDE (CloudCLI)
Docker Sandbox templates that add CloudCLI on top of Claude Code and Codex. You get a full web and mobile IDE accessible from any browser on any device.
Get started
1. Install the sbx CLI
Docker Sandboxes run agents in isolated microVMs. Install the sbx CLI:
- macOS:
brew install docker/tap/sbx - Windows:
winget install -h Docker.sbx - Linux:
sudo apt-get install docker-sbx
Full instructions: docs.docker.com/ai/sandboxes/get-started
2. Store your API key
sbx manages credentials securely — your API key never enters the sandbox. Store it once:
sbx login
sbx secret set -g anthropic
3. Launch Claude Code
npx @cloudcli-ai/cloudcli@latest sandbox ~/my-project
Open http://localhost:3001. Set a password on first visit. Start building.
Using a different agent
Store the matching API key and pass --agent:
# OpenAI Codex
sbx secret set -g openai
npx @cloudcli-ai/cloudcli@latest sandbox ~/my-project --agent codex
Available templates
| Agent | Template |
|---|---|
| Claude Code (default) | docker.io/cloudcliai/sandbox:claude-code |
| OpenAI Codex | docker.io/cloudcliai/sandbox:codex |
These are used with --template when running sbx directly (see Advanced usage).
Managing sandboxes
sbx ls # List all sandboxes
sbx stop my-project # Stop (preserves state)
sbx start my-project # Restart a stopped sandbox
sbx rm my-project # Remove everything
sbx exec my-project bash # Open a shell inside the sandbox
If you install CloudCLI globally (npm install -g @cloudcli-ai/cloudcli), you can also use:
cloudcli sandbox ls
cloudcli sandbox start my-project # Restart and re-launch web UI
cloudcli sandbox logs my-project # View server logs
What you get
- Chat — Markdown rendering, code blocks, message history
- Files — File tree with syntax-highlighted editor
- Git — Diff viewer, staging, branch switching, commits
- Shell — Built-in terminal emulator
- MCP — Configure Model Context Protocol servers visually
- Mobile — Works on tablet and phone browsers
Your project directory is mounted bidirectionally — edits propagate in real time, both ways.
Configuration
Set variables at creation time with --env:
npx @cloudcli-ai/cloudcli@latest sandbox ~/my-project --env SERVER_PORT=8080
Or inside a running sandbox:
sbx exec my-project bash -c 'echo "export SERVER_PORT=8080" >> /etc/sandbox-persistent.sh'
Restart CloudCLI for changes to take effect:
sbx exec my-project bash -c 'pkill -f "server/index.js"'
sbx exec -d my-project cloudcli start --port 3001
| Variable | Default | Description |
|---|---|---|
SERVER_PORT |
3001 |
Web UI port |
HOST |
0.0.0.0 |
Bind address (must be 0.0.0.0 for sbx ports) |
DATABASE_PATH |
~/.cloudcli/auth.db |
SQLite database location |
Advanced usage
For branch mode, multiple workspaces, memory limits, or the terminal agent experience, use sbx with the template:
# Terminal agent + web UI
sbx run --template docker.io/cloudcliai/sandbox:claude-code claude ~/my-project --name my-project
sbx ports my-project --publish 3001:3001
# Branch mode (Git worktree isolation)
sbx run --template docker.io/cloudcliai/sandbox:claude-code claude ~/my-project --branch my-feature
# Multiple workspaces
sbx run --template docker.io/cloudcliai/sandbox:claude-code claude ~/project ~/shared-libs:ro
# Pass a prompt directly
sbx run --template docker.io/cloudcliai/sandbox:claude-code claude ~/my-project -- "Fix the auth bug"
CloudCLI auto-starts via .bashrc when using sbx run.
Full options in the Docker Sandboxes usage guide.
Network policies
Sandboxes restrict outbound access by default. To reach host services from inside the sandbox:
sbx policy allow network localhost:11434
# Inside the sandbox: curl http://host.docker.internal:11434
The web UI itself doesn't need a policy — access it via sbx ports.
Links
- CloudCLI Cloud — fully managed, no setup required
- Documentation — full configuration guide
- Discord — community support
- GitHub — source code and issues
License
AGPL-3.0-or-later