Tests / Test apps.device-host-agent.tests.test_mcp_token.test_load_or_create_concurrent_calls_do_not_corrupt failed
309 lines
9.6 KiB
Python
309 lines
9.6 KiB
Python
from __future__ import annotations
|
|
|
|
from typing import Any
|
|
|
|
import pytest
|
|
|
|
from core.errors import TaskFailedError
|
|
from core.models import Bounds, Scene, SceneElement
|
|
from runtime.ai_planner import AIPlanner
|
|
from runtime.context import TaskContext
|
|
from runtime.executor import StepResult
|
|
from runtime.planner_config import PlannerConfig
|
|
from runtime.tool_calling_client import ToolCallDecision
|
|
from runtime.tool_specs import ALL_TOOL_SPECS
|
|
|
|
|
|
class FakeToolCallingClient:
|
|
def __init__(self, decision: ToolCallDecision) -> None:
|
|
self.decision = decision
|
|
self.calls: list[dict[str, Any]] = []
|
|
|
|
def decide(
|
|
self,
|
|
*,
|
|
system_prompt: str,
|
|
user_prompt: str,
|
|
screenshot: bytes | None,
|
|
tools: list[Any],
|
|
timeout: float,
|
|
history: list[dict[str, Any]] | None = None,
|
|
) -> ToolCallDecision:
|
|
self.calls.append(
|
|
{
|
|
"system_prompt": system_prompt,
|
|
"user_prompt": user_prompt,
|
|
"screenshot": screenshot,
|
|
"tools": tools,
|
|
"timeout": timeout,
|
|
"history": list(history) if history is not None else None,
|
|
}
|
|
)
|
|
return self.decision
|
|
|
|
|
|
def _scene() -> Scene:
|
|
return Scene(
|
|
width=10,
|
|
height=20,
|
|
elements=[
|
|
SceneElement(
|
|
id="send", type="button", text="Send", bounds=Bounds(1, 2, 3, 4)
|
|
)
|
|
],
|
|
)
|
|
|
|
|
|
def _context() -> TaskContext:
|
|
return TaskContext(task_id="task-1", goal="send a message")
|
|
|
|
|
|
def test_ai_planner_returns_single_planned_step_for_action_decision() -> None:
|
|
client = FakeToolCallingClient(
|
|
ToolCallDecision(
|
|
tool_name="tap",
|
|
arguments={"x": 1, "y": 2},
|
|
purpose="Open the send control.",
|
|
expected_outcome="The message composer is focused.",
|
|
)
|
|
)
|
|
planner = AIPlanner(client=client)
|
|
|
|
steps = planner.plan(goal="send a message", scene=_scene(), context=_context())
|
|
|
|
assert len(steps) == 1
|
|
step = steps[0]
|
|
assert step.action == "tap"
|
|
assert step.description == "AI planner: Open the send control."
|
|
assert step.args == {"x": 1, "y": 2}
|
|
assert step.purpose == "Open the send control."
|
|
assert step.expected_outcome == "The message composer is focused."
|
|
assert step.expected_text == "The message composer is focused."
|
|
|
|
|
|
def test_ai_planner_finish_task_success_returns_empty_plan() -> None:
|
|
client = FakeToolCallingClient(
|
|
ToolCallDecision(
|
|
tool_name="finish_task", arguments={"success": True, "reason": "done"}
|
|
)
|
|
)
|
|
planner = AIPlanner(client=client)
|
|
|
|
steps = planner.plan(goal="send a message", scene=_scene(), context=_context())
|
|
|
|
assert steps == []
|
|
|
|
|
|
def test_ai_planner_finish_task_failure_raises_task_failed_error_with_reason() -> None:
|
|
client = FakeToolCallingClient(
|
|
ToolCallDecision(
|
|
tool_name="finish_task",
|
|
arguments={"success": False, "reason": "stuck on login"},
|
|
)
|
|
)
|
|
planner = AIPlanner(client=client)
|
|
|
|
with pytest.raises(TaskFailedError, match="stuck on login"):
|
|
planner.plan(goal="send a message", scene=_scene(), context=_context())
|
|
|
|
|
|
def test_ai_planner_finish_task_failure_without_reason_uses_default_message() -> None:
|
|
client = FakeToolCallingClient(
|
|
ToolCallDecision(tool_name="finish_task", arguments={"success": False})
|
|
)
|
|
planner = AIPlanner(client=client)
|
|
|
|
with pytest.raises(TaskFailedError, match="task failed"):
|
|
planner.plan(goal="send a message", scene=_scene(), context=_context())
|
|
|
|
|
|
def test_ai_planner_goal_reached_is_always_false() -> None:
|
|
client = FakeToolCallingClient(
|
|
ToolCallDecision(tool_name="tap", arguments={"x": 1, "y": 2})
|
|
)
|
|
planner = AIPlanner(client=client)
|
|
|
|
assert (
|
|
planner.goal_reached(goal="anything", scene=_scene(), context=_context())
|
|
is False
|
|
)
|
|
|
|
|
|
def test_ai_planner_forwards_tools_screenshot_and_timeout_to_client() -> None:
|
|
client = FakeToolCallingClient(
|
|
ToolCallDecision(tool_name="tap", arguments={"x": 1, "y": 2})
|
|
)
|
|
planner = AIPlanner(client=client, config=PlannerConfig(timeout=12.5))
|
|
|
|
planner.plan(
|
|
goal="send a message",
|
|
scene=_scene(),
|
|
context=_context(),
|
|
screenshot=b"fake-bytes",
|
|
)
|
|
|
|
call = client.calls[0]
|
|
assert call["tools"] == ALL_TOOL_SPECS
|
|
assert call["screenshot"] == b"fake-bytes"
|
|
assert call["timeout"] == 12.5
|
|
assert "send a message" in call["user_prompt"]
|
|
|
|
|
|
def test_ai_planner_includes_device_platform_from_task_context() -> None:
|
|
client = FakeToolCallingClient(
|
|
ToolCallDecision(tool_name="tap", arguments={"x": 1, "y": 2})
|
|
)
|
|
planner = AIPlanner(client=client)
|
|
context = TaskContext(
|
|
task_id="task-1",
|
|
goal="send a message",
|
|
device_platform="android",
|
|
)
|
|
|
|
planner.plan(goal="send a message", scene=_scene(), context=context)
|
|
|
|
assert "Device type: android" in client.calls[0]["user_prompt"]
|
|
|
|
|
|
def test_ai_planner_populates_step_prompt_from_user_prompt() -> None:
|
|
"""PlannedStep.prompt should carry the actual user prompt sent to the LLM,
|
|
not the bare task goal."""
|
|
client = FakeToolCallingClient(
|
|
ToolCallDecision(tool_name="tap", arguments={"x": 1, "y": 2})
|
|
)
|
|
planner = AIPlanner(client=client)
|
|
|
|
steps = planner.plan(goal="send a message", scene=_scene(), context=_context())
|
|
|
|
assert len(steps) == 1
|
|
assert steps[0].prompt is not None
|
|
# The per-step prompt contains the goal but also scene JSON and instruction text
|
|
assert "send a message" in steps[0].prompt
|
|
assert "Current Scene (JSON)" in steps[0].prompt
|
|
assert "Call exactly one tool" in steps[0].prompt
|
|
|
|
|
|
def test_ai_planner_step_prompt_reflects_scene_changes() -> None:
|
|
"""Per-step prompts differ when the scene changes, proving they are not
|
|
just the repeated task goal."""
|
|
from runtime.context import TaskContext
|
|
|
|
client = FakeToolCallingClient(
|
|
ToolCallDecision(tool_name="tap", arguments={"x": 1, "y": 2})
|
|
)
|
|
planner = AIPlanner(client=client)
|
|
|
|
scene_a = Scene(
|
|
width=10,
|
|
height=20,
|
|
elements=[
|
|
SceneElement(
|
|
id="btn_a", type="button", text="Alpha", bounds=Bounds(1, 2, 3, 4)
|
|
)
|
|
],
|
|
)
|
|
scene_b = Scene(
|
|
width=10,
|
|
height=20,
|
|
elements=[
|
|
SceneElement(
|
|
id="btn_b", type="button", text="Beta", bounds=Bounds(5, 6, 7, 8)
|
|
)
|
|
],
|
|
)
|
|
|
|
steps_a = planner.plan(
|
|
goal="test", scene=scene_a, context=TaskContext(task_id="t", goal="test")
|
|
)
|
|
steps_b = planner.plan(
|
|
goal="test", scene=scene_b, context=TaskContext(task_id="t", goal="test")
|
|
)
|
|
|
|
assert steps_a[0].prompt != steps_b[0].prompt
|
|
assert "Alpha" in steps_a[0].prompt
|
|
assert "Beta" in steps_b[0].prompt
|
|
|
|
|
|
def test_ai_planner_propagates_rationale_and_thinking_to_planned_step() -> None:
|
|
client = FakeToolCallingClient(
|
|
ToolCallDecision(
|
|
tool_name="tap",
|
|
arguments={"x": 1, "y": 2},
|
|
text_output="Previous step opened settings. Now tapping account.",
|
|
thinking="I need to navigate deeper.",
|
|
purpose="Open account settings.",
|
|
expected_outcome="The account settings page is visible.",
|
|
)
|
|
)
|
|
planner = AIPlanner(client=client)
|
|
|
|
steps = planner.plan(goal="open account", scene=_scene(), context=_context())
|
|
|
|
assert steps[0].rationale == "Previous step opened settings. Now tapping account."
|
|
assert steps[0].thinking == "I need to navigate deeper."
|
|
assert steps[0].purpose == "Open account settings."
|
|
assert steps[0].expected_outcome == "The account settings page is visible."
|
|
|
|
|
|
def test_ai_planner_carries_completed_turn_into_the_next_llm_call() -> None:
|
|
client = FakeToolCallingClient(
|
|
ToolCallDecision(
|
|
tool_name="tap",
|
|
arguments={"x": 1, "y": 2},
|
|
text_output="Opening the send control.",
|
|
purpose="Open the send control.",
|
|
expected_outcome="The composer is focused.",
|
|
)
|
|
)
|
|
planner = AIPlanner(client=client)
|
|
context = _context()
|
|
|
|
first_step = planner.plan(goal=context.goal, scene=_scene(), context=context)[0]
|
|
context.add_step_result(
|
|
StepResult(
|
|
step=first_step,
|
|
success=True,
|
|
attempts=1,
|
|
result={"ok": True},
|
|
)
|
|
)
|
|
planner.plan(goal=context.goal, scene=_scene(), context=context)
|
|
|
|
assert client.calls[0]["history"] == []
|
|
history = client.calls[1]["history"]
|
|
assert history is not None
|
|
assert history[0]["tool_name"] == "tap"
|
|
assert history[0]["arguments"] == {
|
|
"x": 1,
|
|
"y": 2,
|
|
"purpose": "Open the send control.",
|
|
"expected_outcome": "The composer is focused.",
|
|
}
|
|
assert history[0]["tool_result"]["success"] is True
|
|
assert history[0]["tool_result"]["result"] == {"ok": True}
|
|
|
|
|
|
def test_ai_planner_limits_history_sent_to_the_llm() -> None:
|
|
client = FakeToolCallingClient(
|
|
ToolCallDecision(tool_name="tap", arguments={"x": 1, "y": 2})
|
|
)
|
|
planner = AIPlanner(client=client, config=PlannerConfig(history_max_turns=2))
|
|
context = _context()
|
|
context.planner_history.extend(
|
|
{
|
|
"user_prompt": f"turn-{index}",
|
|
"tool_name": "tap",
|
|
"arguments": {},
|
|
"rationale": None,
|
|
"tool_result": {"success": True},
|
|
}
|
|
for index in range(3)
|
|
)
|
|
|
|
planner.plan(goal=context.goal, scene=_scene(), context=context)
|
|
|
|
assert [turn["user_prompt"] for turn in client.calls[0]["history"]] == [
|
|
"turn-1",
|
|
"turn-2",
|
|
]
|