Trước đây công tắc chỉ chặn tool mạng của agent; lệnh shell chỉ bị proxy giả, còn M365, Teams, nút Test, MCP đang chạy, task script, link đính kèm task, pip tự cài và tài nguyên web trong xem trước HTML vẫn ra mạng tự do. - Cổng chung application/network/network_guard.py, nối vào cấu hình sống ở Composition Root; nhà cung cấp AI (chat, danh sách model, thử model) không đi qua cổng này. - Lệnh shell của agent và task script chạy trong Windows AppContainer không có quyền mạng (macOS: sandbox-exec, Linux: unshare --net); không cô lập được thì từ chối chạy. - Không cấp quyền kế thừa của AppContainer lên thư mục chứa PySide6: Chromium không nạp được Qt6WebEngineCore.dll và tab Graph bị hỏng. - Bật chặn thì dừng MCP đang chạy; tool OneDrive đồng bộ trên máy vẫn dùng. - Mặc định tắt khi mở app lần đầu; nhãn và tooltip 3 ngôn ngữ cập nhật. - Test: tests/test_network_guard_lanes.py (có bài AppContainer thật). Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Cowork Local
Cowork Local is the internal AI cowork desktop platform. It provides a local-first desktop runtime, multi-turn conversational agents, workspace isolation, task scheduling, MCP connectors, security guardrails, and model routing.
🏛️ 4-Tier Clean Architecture
The codebase strictly adheres to Clean Architecture with unidirectional inward dependencies:
presentation/ (PySide6 UI, Shell, NavRail, Chat, Scheduling, Settings, Dashboard)
│
▼
application/ (Pure Python Orchestration: Conversations, Scheduling, Workspaces, Monitoring, Routing)
│
▼
domain/ (Pure Python: Entities, Immutable Execution Requests, Agent Events, Descriptors)
▲
│
infrastructure/ (Adapters, LLM Providers, Atomic Persistence, Keyring SecretStore, MCP)
- Domain & Application Layers: 100% Pure Python (zero Qt/UI imports).
- Single Responsibility: Every production module is strictly
<= 400 LOC. - Security & Durability: API keys stored in OS Keyring; atomic JSON disk persistence.
🚀 Quick Start
1. Windows — two double-clicks
install.bat once, to install the Python dependencies
run.bat every time, to start the app
install.bat builds an isolated virtualenv under %LOCALAPPDATA%\CoworkLocal
(deliberately outside the repo — the quality gates walk the whole directory
tree, so a .venv in here would turn every vendored module into a Gate O
violation). Add --dev to also install the test dependencies, or --system to
skip the virtualenv and install into the Python already on PATH.
Both scripts also make the source importable under its package name. That step
is not optional: python -m cowork_local only resolves when the checkout
directory is literally named cowork_local, and the MS365 MCP server is
launched as a subprocess with python -m cowork_local.mcp_servers.ms365_server,
so a differently-named checkout breaks the app and its subprocesses. The
scripts create a junction instead of forcing anyone to rename their folder.
2. Any platform — run from source
From the parent of a checkout directory named cowork_local:
python -m cowork_local
3. Run Automated Tests
python -m pip install -r requirements.txt
pytest -q
There is one requirements file, not a runtime/test pair. A separate test file
would hold only pytest: 64 of the 108 test modules build real widgets, and 20
of them import PySide6 unguarded at module scope, so it would have to pull in
almost the whole runtime list anyway — two files for one near-identical list is
just a second place for the pins to drift.
🛡️ CASAN Quality Gate & Verification
Before submitting any Pull Request, run the unified CASAN Quality Gate:
# Run all 4 quality gates (Clean Arch, Secrets, LOC, and Pytest Suite)
python scripts/run_quality_gate.py
# Run static and architectural guards only (fast check)
python scripts/run_quality_gate.py --skip-tests
Individual guard scripts:
- Clean Architecture Import Guard:
python scripts/check_imports.py - Secrets & Plaintext Audit:
python scripts/audit_security.py - Single Responsibility LOC Guard:
python scripts/check_loc.py --max-lines 400 - Release E2E Smoke Test:
pytest tests/e2e/test_smoke.py -v
🤝 Contributing & Recipes
- Quick Start Guide: See START_CONTRIBUTING.md.
- Contributor Recipes: See docs/governance/contributor-recipes.md for step-by-step recipes to:
- Add a new AI Model Provider.
- Add a new Built-in Tool / MCP Server.
- Add a new Screen / Tab / Widget.
- Security Policy: See SECURITY.md.