Four features, plus a latent bug fix.
llama.cpp backend. Claude Code only ever speaks the Anthropic Messages
API — confirmed empirically by pointing it at a logging server, which
received POST /v1/messages?beta=true. llama-server implements that
natively (verified in its README, alongside --port default 8080), so
this is a plain base-URL backend with no translation shim, the same
shape as Ollama. Its --api-key defaults to none, so the auth token is a
placeholder Claude Code requires and llama-server ignores.
Model alias fix. ANTHROPIC_DEFAULT_HAIKU_MODEL is documented as "also
used for background functionality", and Triple-C set none of the alias
vars. So on every custom-endpoint backend, Claude Code resolved `haiku`
to an Anthropic model id and sent it to a local server that does not
have it — background features failed silently. All four
ANTHROPIC_DEFAULT_{OPUS,SONNET,HAIKU,FABLE}_MODEL vars are now pinned to
the backend's configured model, with an optional Haiku override, and
blanked for Anthropic and Bedrock so those keep Claude Code's defaults.
The deprecated ANTHROPIC_SMALL_FAST_MODEL is never emitted. Existing
Ollama and OpenAI-Compatible containers are recreated once so the new
env reaches them; the snapshot is preserved.
Model gateway. Optional LiteLLM sibling container, off by default,
mirroring stt.rs — this is what makes real OpenAI usable, since
api.openai.com has no /v1/messages. Pinned to v1.96.0 by tag and digest:
the 1.82.7/1.82.8 malware was PyPI-only and never affected the official
images, which is precisely why this builds FROM the image rather than
pip-installing, but 1.84.0 is still the floor for proxy CVEs (API-key
SQLi, Host-header auth bypass, MCP auth bypass). Binds 0.0.0.0 because
project containers consume it, and therefore always sets a master_key —
LiteLLM without one accepts any key. The provider key lives in the OS
keychain and is uploaded into a volume, never an image layer or label.
URL relay. A container-side xdg-open/BROWSER shim opens URLs in the
host's browser. Uses an OSC sequence to /dev/tty rather than a printed
sentinel, because the shim usually runs as a grandchild of a process
capturing its children's output. Degrades to printing the URL when no
terminal is attached, so scheduled tasks do not hang. Only http/https,
with control characters rejected before new URL() — which strips
newlines, so java\nscript: would otherwise parse as javascript:. Nothing
auto-opens; the user confirms. The web terminal shows a tap-to-open
banner instead, since that browser may be a phone across a tunnel.
Browser view. A Project Home tab that watches and takes over the browser
Claude drives with Playwright, using Playwright's own dashboard. Zero
image cost — Playwright stays user-installed. It does not reuse the auth
bridge's PortForward, which binds an unauthenticated port: correct for a
throwaway OAuth listener, wrong for mouse and keyboard control of a
browser in a passwordless-sudo container. Instead a token-gated loopback
proxy checks Host, then token or a forbidden-header origin signal,
before a byte reaches the container. Host ports are confined to
47820..=47827 so CSP frame-src can enumerate them rather than widening
to a wildcard, with a test asserting the two agree.
188 frontend tests, 107 Rust tests, both builds clean.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
## What's New in v0.3.0
### Claude Code Settings (TUI Mode, Effort, Focus, Caching)
- New per-project and global settings for Claude Code CLI behavior
- **TUI Fullscreen Mode**: Flicker-free alt-screen rendering via CLAUDE_CODE_NO_FLICKER
- **Effort Level**: Control reasoning depth (low/medium/high)
- **Focus Mode**: Collapse tool output to one-line summaries
- **Thinking Summaries**: Show Claude's thinking process
- **Session Recap**: Get context when returning to a session
- **Auto-Scroll Disabled**: Disable auto-scroll in fullscreen TUI
- **Env Scrub**: Strip credentials from subprocess environments
- **Prompt Caching (1h)**: Enable 1-hour prompt cache TTL
- New ClaudeCodeSettingsModal accessible from project config and global settings
- Settings injected as env vars and ~/.claude/settings.json via entrypoint
### Session Naming
- Name Claude Code terminal sessions with the -n flag
- Session names displayed in terminal tabs instead of project name
### Global Default Fallbacks
- Global SSH key path now used when per-project SSH path is not set
- Global git name/email now used when per-project values are not set
- New UI in Settings panel for SSH key directory, git name, and git email
### Relaxed Environment Variable Filter
- CLAUDE_CODE_* env vars now allowed in custom env vars for power users
- Only specific internal vars (CLAUDE_INSTRUCTIONS, MCP_SERVERS_JSON, etc.) blocked
### Documentation
- Updated README, HOW-TO-USE, and CLAUDE.md with all new features
- New "Claude Code Tips" section documenting built-in CLI features
(/focus, /recap, /color, /loop, /powerup, /team-onboarding, setup wizards)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add two new auth modes for projects alongside Anthropic and Bedrock:
- Ollama: connect to local or remote Ollama servers via ANTHROPIC_BASE_URL
- LiteLLM: connect through a LiteLLM proxy gateway to 100+ model providers
Both modes inject ANTHROPIC_BASE_URL and ANTHROPIC_AUTH_TOKEN env vars into
the container, with optional model override via ANTHROPIC_MODEL. LiteLLM
API keys are stored securely in the OS keychain. Config changes trigger
automatic container recreation via fingerprinting.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The previous approach used Builder::default_window_icon() which doesn't
exist in Tauri 2.10. Instead, set the icon via window.set_icon() in the
setup hook, and enable the "image-png" feature flag so Image::from_bytes
can decode the PNG icon at runtime.
Also change bundle identifier from "com.triple-c.app" to
"com.triple-c.desktop" to avoid conflicting with the .app bundle
extension on macOS.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Enable restrictive Content Security Policy in tauri.conf.json instead
of null (disabled), restricting scripts/connects to self + Tauri IPC
- Fix shell injection in entrypoint.sh by replacing su -c with direct
git config --file writes, preventing names with quotes (e.g. O'Brien)
from breaking startup or enabling code execution
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Windows requires icon.ico for the resource file during tauri-build.
Generated from existing 128x128@2x.png placeholder.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Tauri v2 desktop app (React/TypeScript + Rust) for managing
containerized Claude Code environments. Includes Gitea Actions
workflow for building and pushing the sandbox container image,
and a BUILDING.md guide for manual app builds on Linux and Windows.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
shadow-testandClaude Opus 5
