vudt15andClaude Sonnet 5
ae4fe72b2e
EPIC R05 (Team Hoa) - one security/approval path for every tool call.
R05-T01 domain/tools/{tool_descriptor,tool_registry}.py
ToolCapability (READ/WRITE/EXECUTE/NETWORK, composable) + ToolDescriptor +
ToolRegistry, replacing three independently-maintained gating lists
(core/tools.py::WRITE_TOOLS, code_agent.py's WRITE_TOOLS|MS365_WRITE_TOOLS,
chat_agent.py's literal ("run_command","install_package") tuple) with one
capability lookup.
R05-T02 infrastructure/filesystem/{file_tools,command_tools,fetch_tools,tool_context}.py
core/tools.py's execute_tool if/elif chain split into per-concern modules.
core/tools.py is now a strangler-fig shim: re-exports ToolContext/ToolError,
dispatches through a {name: handler} dict built from the split modules.
core/tools.py: 566 -> 291 lines.
R05-T03 application/conversations/tool_policy_gateway.py
ToolPolicyGateway.allow(name, gate, payload) - capability-driven ALLOW vs
ask-the-gate decision. Wired into both chat_agent.py::run_cowork and
code_agent.py::run_code, replacing their separate hand-rolled checks.
Verified equivalent to the old hardcoded sets by test.
R05-T04 (behavior change, not just refactor)
MCP/connector tools (core/mcp_client.py, core/ext_connectors.py) reached
chat_agent.py via extra_executor(name, args) with NO permission check at
all. They are now tagged with a conservative default capability
(WRITE|EXECUTE|NETWORK - no MCP tool self-declares risk) and routed through
the SAME ToolPolicyGateway as built-ins. When "confirm before running
commands" is on, MCP/connector calls now prompt like run_command already
did - a real gap closed, and a user-visible change worth calling out.
R05-T05 infrastructure/mcp/mcp_source_manager.py
McpToolSourceManager extracts the connection cache/lock/start-or-skip
lifecycle out of state.py::AppContext (_mcp_connections/_conn_lock) into a
standalone, directly-testable class. AppContext.build_mcp_tools and
_ms365_builtin_connection now call ensure()/stop(); _ext_connections
(unified Connectors) is out of scope for this task and keeps its own lock.
New tests: tests/unit/test_tool_registry_and_policy.py,
test_code_agent_tool_policy.py, test_cowork_extra_tool_policy.py,
test_mcp_source_manager.py (26 new tests).
Suite: 254 passed, 4 pre-existing failures unrelated to R05 (2 EPIC R02
config-security, 2 environment-dependent routing tests - see checklist).
check_imports: PASS. All new files < 400 LOC.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Cowork Local
Cowork Local is the internal AI cowork desktop platform owned by the Cowork Team. It provides the Cowork runtime, workspace and agent experiences, MCP/connectors, security controls, and model routing foundation.
The Cowork Team owns this product and its stable branch. The FSG AI Core Team contributes selected reusable capabilities through branches and Pull Requests; it is not the owner or final merger of this repository.
Quick start
The imported application is a Python/PySide6 package. Run it from the directory that contains cowork_local:
python -m cowork_local
The source snapshot does not include a complete runtime dependency manifest. Use the Cowork Team's supported runtime environment until that packaging contract is documented. The reliable automated test surface currently checked by CI is:
python -m pip install -r cowork_local/requirements-test.txt
python -m pytest cowork_local/tests -q
When already inside this repository, run python -m pytest tests -q.
Configuration and runtime data live under ~/.cowork_local/. Provider keys and local unlock codes must be supplied through environment variables or an approved secret manager; see .env.example.
Contributing
Start with START_CONTRIBUTING.md, then read CONTRIBUTING.md. Core AI task execution remains in fsg-ai-core-assets; source changes are reviewed as Pull Requests in this repository.
Security concerns should follow SECURITY.md. Ownership and completion rules are documented under docs/governance/.