feat(host-agent): wrap tool_handlers with busy check + status mapping

This commit is contained in:
2026-07-21 14:09:42 +08:00
parent cf8affe4d7
commit b73db01626
2 changed files with 462 additions and 0 deletions
@@ -0,0 +1,226 @@
from __future__ import annotations
from datetime import UTC, datetime
from typing import Any
import pytest
from cloud.internal_api.models import AssignmentModel
from device.manager import DeviceManager
from driver.base import Driver
from host_agent.mcp_lock import McpBusyTracker
from host_agent.status import AgentStatusTracker
from host_agent.web.mcp import (
McpDeviceBusyError,
_call_tool_sync,
build_mcp_server,
)
class _FakeDriver(Driver):
"""Minimal driver. connect/screenshot/tap are exercised; remaining abstract
methods are stubbed to satisfy Driver's ABC contract."""
def __init__(self) -> None:
self.taps: list[tuple[float, float]] = []
def connect(self) -> None:
return None
def disconnect(self) -> None:
return None
def screenshot(self) -> bytes:
return b"fake"
def tap(self, x: float, y: float) -> None:
self.taps.append((x, y))
def long_press(self, x: float, y: float, duration_ms: int = 1200) -> None:
return None
def swipe(
self,
start_x: float,
start_y: float,
end_x: float,
end_y: float,
duration_ms: int = 500,
) -> None:
return None
def swipe_path(self, waypoints: list[tuple[float, float]], duration_ms: int) -> None:
return None
def double_tap(self, x: float, y: float, interval_ms: int = 80) -> None:
return None
def input(self, text: str) -> None:
return None
def launch(self, app_id: str) -> None:
return None
def terminate(self, app_id: str) -> None:
return None
def tree(self) -> Any:
return None
def home(self) -> None:
return None
def lock(self) -> None:
return None
def unlock(self) -> None:
return None
def _make_manager_with_device(device_id: str = "phone-1") -> DeviceManager:
manager = DeviceManager()
manager.register_device(
device_id=device_id,
driver_factory=lambda: _FakeDriver(),
name=device_id,
)
manager.connect(device_id)
return manager
def test_build_mcp_server_returns_fastmcp_instance() -> None:
from mcp.server.fastmcp import FastMCP
manager = _make_manager_with_device()
tracker = McpBusyTracker()
status = AgentStatusTracker()
server = build_mcp_server(
manager=manager, mcp_busy_tracker=tracker, status_tracker=status
)
assert isinstance(server, FastMCP)
def test_call_tool_succeeds_when_device_is_free() -> None:
manager = _make_manager_with_device()
tracker = McpBusyTracker()
status = AgentStatusTracker()
server = build_mcp_server(
manager=manager, mcp_busy_tracker=tracker, status_tracker=status
)
result = _call_tool_sync(
server, "take_screenshot", {"device_id": "phone-1"}, session_id="sess-a"
)
assert result["ok"] is True
assert "phone-1" in tracker.busy_device_ids()
def test_call_tool_fails_when_cloud_uses_device() -> None:
"""AgentStatusTracker.current_assignment.device_id matches -> busy."""
manager = _make_manager_with_device()
tracker = McpBusyTracker()
status = AgentStatusTracker()
status.mark_assignment_started(
AssignmentModel(
task_id="t1",
attempt=1,
lease_id="l1",
lease_expires_at=datetime.now(UTC),
host_id="h1",
device_id="phone-1",
goal="cloud task",
)
)
server = build_mcp_server(
manager=manager, mcp_busy_tracker=tracker, status_tracker=status
)
with pytest.raises(McpDeviceBusyError) as exc:
_call_tool_sync(
server,
"take_screenshot",
{"device_id": "phone-1"},
session_id="sess-a",
)
assert exc.value.device_id == "phone-1"
assert exc.value.busy_owner == "cloud_assignment"
def test_call_tool_fails_when_another_mcp_session_holds_device() -> None:
manager = _make_manager_with_device()
tracker = McpBusyTracker()
status = AgentStatusTracker()
# Pre-acquire as a different session.
tracker.acquire("phone-1", "sess-other")
server = build_mcp_server(
manager=manager, mcp_busy_tracker=tracker, status_tracker=status
)
with pytest.raises(McpDeviceBusyError) as exc:
_call_tool_sync(
server,
"take_screenshot",
{"device_id": "phone-1"},
session_id="sess-a",
)
assert exc.value.busy_owner.startswith("mcp_session:")
def test_call_tool_renews_when_same_session_already_holds() -> None:
manager = _make_manager_with_device()
tracker = McpBusyTracker()
status = AgentStatusTracker()
server = build_mcp_server(
manager=manager, mcp_busy_tracker=tracker, status_tracker=status
)
_call_tool_sync(
server, "take_screenshot", {"device_id": "phone-1"}, session_id="sess-a"
)
# Second call from the same session should succeed.
result = _call_tool_sync(
server, "take_screenshot", {"device_id": "phone-1"}, session_id="sess-a"
)
assert result["ok"] is True
def test_list_devices_uses_display_status() -> None:
"""Connected-but-idle devices report as 'connected', not 'busy'."""
manager = _make_manager_with_device()
tracker = McpBusyTracker()
status = AgentStatusTracker()
server = build_mcp_server(
manager=manager, mcp_busy_tracker=tracker, status_tracker=status
)
result = _call_tool_sync(server, "list_devices", {}, session_id="sess-a")
assert isinstance(result, list)
assert result[0]["status"] == "connected"
def test_unknown_device_returns_semantic_error_dict() -> None:
"""take_screenshot against an unknown device returns the api-errors semantic
error dict (``ok=False, error="device not found"``) rather than raising.
Note: this test adapts the brief's exception-assertion semantics to the
actual behavior of ``call_with_semantic_errors`` in ``api/errors.py`` —
the brief's expectation that an exception is raised here is incorrect for
the current handler implementation."""
manager = _make_manager_with_device()
tracker = McpBusyTracker()
status = AgentStatusTracker()
server = build_mcp_server(
manager=manager, mcp_busy_tracker=tracker, status_tracker=status
)
result = _call_tool_sync(
server,
"take_screenshot",
{"device_id": "does-not-exist"},
session_id="sess-a",
)
assert isinstance(result, dict)
assert result["ok"] is False
assert "device" in result["error"].lower()
def test_manager_required_for_build_mcp_server() -> None:
"""Reinforces D12 — build_mcp_server requires manager as keyword-only."""
import inspect
sig = inspect.signature(build_mcp_server)
assert sig.parameters["manager"].kind == inspect.Parameter.KEYWORD_ONLY