Files
cowork-local/infrastructure/filesystem/command_tools.py
T
vudt15andClaude Sonnet 5 ae4fe72b2e feat(R05): tool capability registry, unified policy gateway, MCP lifecycle manager
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>
2026-08-21 22:20:57 +09:00

111 lines
4.3 KiB
Python

"""Command tools - run_command, install_package (R05-T02).
Moved verbatim out of ``core/tools.py`` (see ``file_tools.py`` for why). These
two are the ones today's hand-written permission gate in
``core/chat_agent.py`` singles out by literal name
(``name in ("run_command", "install_package")``) — R05-T03 replaces that
tuple with a capability lookup, but the tools themselves are unchanged here.
"""
from __future__ import annotations
import os
from pathlib import Path
from typing import Any, Dict, Optional
from .tool_context import CancelFn, ToolContext
COMMAND_TIMEOUT = 120 # seconds
_SNAPSHOT_SKIP = {".git", "__pycache__", "node_modules", ".scratch", ".venv",
".idea", ".mypy_cache", ".pytest_cache"}
def _snapshot(workdir: Path) -> Dict[str, Any]:
"""Map of file path -> (mtime, size) under the workdir (noise dirs skipped)."""
snap: Dict[str, Any] = {}
try:
for dirpath, dirnames, filenames in os.walk(str(workdir)):
dirnames[:] = [d for d in dirnames if d not in _SNAPSHOT_SKIP]
for fn in filenames:
full = os.path.join(dirpath, fn)
try:
st = os.stat(full)
snap[full] = (st.st_mtime_ns, st.st_size)
except OSError:
pass
if len(snap) > 5000:
return snap
except OSError:
pass
return snap
def _sandbox_python(ctx: ToolContext, cancel: Optional[CancelFn] = None,
on_output=None) -> Optional[str]:
"""Lazily create/reuse this ctx's project sandbox venv (Code tab only —
``ctx.sandbox``); returns its python path, or None to use the app's own."""
if not ctx.sandbox:
return None
from cowork_local.core.deps import ensure_project_venv
py = ensure_project_venv(ctx.workdir, cancel=cancel, on_output=on_output)
return str(py) if py else None
def run_command(ctx: ToolContext, args: Dict[str, Any],
cancel: Optional[CancelFn] = None,
on_output=None) -> Dict[str, Any]:
from cowork_local.core.deps import network_blocked_env, run_cancellable, sandbox_env
from cowork_local.core.sandbox_manager import ExecutionConfig, SandboxManager
from cowork_local.security.command_risk_classifier import classify_command
command = str(args.get("command", "")).strip()
if not command:
return {"ok": False, "output": "Empty command."}
# --- Security validation pipeline ---
risk = classify_command(command, is_cowork_mode=ctx.flatten_writes)
if risk.blocked:
denial = "Command blocked by security policy: " + "; ".join(risk.reasons)
return {"ok": False, "output": denial}
# Route through SandboxManager for risk-based isolation
mgr = SandboxManager(ExecutionConfig(
enabled=True,
block_network_by_default=ctx.block_network,
is_cowork_mode=ctx.flatten_writes,
))
sandbox_result = mgr.run(
command=command,
workdir=str(ctx.workdir),
block_network=ctx.block_network,
timeout_sec=COMMAND_TIMEOUT,
cancel=cancel,
)
# Sandbox ALWAYS executes (never double-run). Return its result directly.
if sandbox_result.get("sandbox") == "blocked":
return {"ok": False, "output": sandbox_result.get("stderr", "Command blocked")}
out = sandbox_result.get("stdout", "").strip() or "(no output)"
err = sandbox_result.get("stderr", "")
rc = sandbox_result.get("returncode", -1)
if err:
out = f"{out}\n{err}" if out else err
return {"ok": sandbox_result.get("ok", False), "output": f"[exit {rc}]\n{out}"}
def install_package(ctx: ToolContext, args: Dict[str, Any],
cancel: Optional[CancelFn] = None,
on_output=None) -> Dict[str, Any]:
from cowork_local.core.deps import pip_install
package = str(args.get("package", "")).strip()
if not package:
return {"ok": False, "output": "No package specified."}
python = _sandbox_python(ctx, cancel, on_output)
ok, detail = pip_install(package, cancel=cancel, on_output=on_output, python=python)
head = f"Installed {package}." if ok else f"Could not install {package}."
return {"ok": ok, "output": f"{head}\n{detail}"}
__all__ = ["COMMAND_TIMEOUT", "run_command", "install_package", "_snapshot"]