mirror of
https://github.com/HKUDS/nanobot.git
synced 2026-04-02 17:32:39 +00:00
351e3720b6
Add a regression test for the maintainer fix so subagents cannot register ExecTool when exec support is disabled. Made-with: Cursor
338 lines
12 KiB
Python
338 lines
12 KiB
Python
"""Tests for /stop task cancellation."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import asyncio
|
|
from types import SimpleNamespace
|
|
from unittest.mock import AsyncMock, MagicMock, patch
|
|
|
|
import pytest
|
|
|
|
|
|
def _make_loop(*, exec_config=None):
|
|
"""Create a minimal AgentLoop with mocked dependencies."""
|
|
from nanobot.agent.loop import AgentLoop
|
|
from nanobot.bus.queue import MessageBus
|
|
|
|
bus = MessageBus()
|
|
provider = MagicMock()
|
|
provider.get_default_model.return_value = "test-model"
|
|
workspace = MagicMock()
|
|
workspace.__truediv__ = MagicMock(return_value=MagicMock())
|
|
|
|
with patch("nanobot.agent.loop.ContextBuilder"), \
|
|
patch("nanobot.agent.loop.SessionManager"), \
|
|
patch("nanobot.agent.loop.SubagentManager") as MockSubMgr:
|
|
MockSubMgr.return_value.cancel_by_session = AsyncMock(return_value=0)
|
|
loop = AgentLoop(bus=bus, provider=provider, workspace=workspace, exec_config=exec_config)
|
|
return loop, bus
|
|
|
|
|
|
class TestHandleStop:
|
|
@pytest.mark.asyncio
|
|
async def test_stop_no_active_task(self):
|
|
from nanobot.bus.events import InboundMessage
|
|
from nanobot.command.builtin import cmd_stop
|
|
from nanobot.command.router import CommandContext
|
|
|
|
loop, bus = _make_loop()
|
|
msg = InboundMessage(channel="test", sender_id="u1", chat_id="c1", content="/stop")
|
|
ctx = CommandContext(msg=msg, session=None, key=msg.session_key, raw="/stop", loop=loop)
|
|
out = await cmd_stop(ctx)
|
|
assert "No active task" in out.content
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_stop_cancels_active_task(self):
|
|
from nanobot.bus.events import InboundMessage
|
|
from nanobot.command.builtin import cmd_stop
|
|
from nanobot.command.router import CommandContext
|
|
|
|
loop, bus = _make_loop()
|
|
cancelled = asyncio.Event()
|
|
|
|
async def slow_task():
|
|
try:
|
|
await asyncio.sleep(60)
|
|
except asyncio.CancelledError:
|
|
cancelled.set()
|
|
raise
|
|
|
|
task = asyncio.create_task(slow_task())
|
|
await asyncio.sleep(0)
|
|
loop._active_tasks["test:c1"] = [task]
|
|
|
|
msg = InboundMessage(channel="test", sender_id="u1", chat_id="c1", content="/stop")
|
|
ctx = CommandContext(msg=msg, session=None, key=msg.session_key, raw="/stop", loop=loop)
|
|
out = await cmd_stop(ctx)
|
|
|
|
assert cancelled.is_set()
|
|
assert "stopped" in out.content.lower()
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_stop_cancels_multiple_tasks(self):
|
|
from nanobot.bus.events import InboundMessage
|
|
from nanobot.command.builtin import cmd_stop
|
|
from nanobot.command.router import CommandContext
|
|
|
|
loop, bus = _make_loop()
|
|
events = [asyncio.Event(), asyncio.Event()]
|
|
|
|
async def slow(idx):
|
|
try:
|
|
await asyncio.sleep(60)
|
|
except asyncio.CancelledError:
|
|
events[idx].set()
|
|
raise
|
|
|
|
tasks = [asyncio.create_task(slow(i)) for i in range(2)]
|
|
await asyncio.sleep(0)
|
|
loop._active_tasks["test:c1"] = tasks
|
|
|
|
msg = InboundMessage(channel="test", sender_id="u1", chat_id="c1", content="/stop")
|
|
ctx = CommandContext(msg=msg, session=None, key=msg.session_key, raw="/stop", loop=loop)
|
|
out = await cmd_stop(ctx)
|
|
|
|
assert all(e.is_set() for e in events)
|
|
assert "2 task" in out.content
|
|
|
|
|
|
class TestDispatch:
|
|
def test_exec_tool_not_registered_when_disabled(self):
|
|
from nanobot.config.schema import ExecToolConfig
|
|
|
|
loop, _bus = _make_loop(exec_config=ExecToolConfig(enable=False))
|
|
|
|
assert loop.tools.get("exec") is None
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_dispatch_processes_and_publishes(self):
|
|
from nanobot.bus.events import InboundMessage, OutboundMessage
|
|
|
|
loop, bus = _make_loop()
|
|
msg = InboundMessage(channel="test", sender_id="u1", chat_id="c1", content="hello")
|
|
loop._process_message = AsyncMock(
|
|
return_value=OutboundMessage(channel="test", chat_id="c1", content="hi")
|
|
)
|
|
await loop._dispatch(msg)
|
|
out = await asyncio.wait_for(bus.consume_outbound(), timeout=1.0)
|
|
assert out.content == "hi"
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_processing_lock_serializes(self):
|
|
from nanobot.bus.events import InboundMessage, OutboundMessage
|
|
|
|
loop, bus = _make_loop()
|
|
order = []
|
|
|
|
async def mock_process(m, **kwargs):
|
|
order.append(f"start-{m.content}")
|
|
await asyncio.sleep(0.05)
|
|
order.append(f"end-{m.content}")
|
|
return OutboundMessage(channel="test", chat_id="c1", content=m.content)
|
|
|
|
loop._process_message = mock_process
|
|
msg1 = InboundMessage(channel="test", sender_id="u1", chat_id="c1", content="a")
|
|
msg2 = InboundMessage(channel="test", sender_id="u1", chat_id="c1", content="b")
|
|
|
|
t1 = asyncio.create_task(loop._dispatch(msg1))
|
|
t2 = asyncio.create_task(loop._dispatch(msg2))
|
|
await asyncio.gather(t1, t2)
|
|
assert order == ["start-a", "end-a", "start-b", "end-b"]
|
|
|
|
|
|
class TestSubagentCancellation:
|
|
@pytest.mark.asyncio
|
|
async def test_cancel_by_session(self):
|
|
from nanobot.agent.subagent import SubagentManager
|
|
from nanobot.bus.queue import MessageBus
|
|
|
|
bus = MessageBus()
|
|
provider = MagicMock()
|
|
provider.get_default_model.return_value = "test-model"
|
|
mgr = SubagentManager(provider=provider, workspace=MagicMock(), bus=bus)
|
|
|
|
cancelled = asyncio.Event()
|
|
|
|
async def slow():
|
|
try:
|
|
await asyncio.sleep(60)
|
|
except asyncio.CancelledError:
|
|
cancelled.set()
|
|
raise
|
|
|
|
task = asyncio.create_task(slow())
|
|
await asyncio.sleep(0)
|
|
mgr._running_tasks["sub-1"] = task
|
|
mgr._session_tasks["test:c1"] = {"sub-1"}
|
|
|
|
count = await mgr.cancel_by_session("test:c1")
|
|
assert count == 1
|
|
assert cancelled.is_set()
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_cancel_by_session_no_tasks(self):
|
|
from nanobot.agent.subagent import SubagentManager
|
|
from nanobot.bus.queue import MessageBus
|
|
|
|
bus = MessageBus()
|
|
provider = MagicMock()
|
|
provider.get_default_model.return_value = "test-model"
|
|
mgr = SubagentManager(provider=provider, workspace=MagicMock(), bus=bus)
|
|
assert await mgr.cancel_by_session("nonexistent") == 0
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_subagent_preserves_reasoning_fields_in_tool_turn(self, monkeypatch, tmp_path):
|
|
from nanobot.agent.subagent import SubagentManager
|
|
from nanobot.bus.queue import MessageBus
|
|
from nanobot.providers.base import LLMResponse, ToolCallRequest
|
|
|
|
bus = MessageBus()
|
|
provider = MagicMock()
|
|
provider.get_default_model.return_value = "test-model"
|
|
|
|
captured_second_call: list[dict] = []
|
|
|
|
call_count = {"n": 0}
|
|
|
|
async def scripted_chat_with_retry(*, messages, **kwargs):
|
|
call_count["n"] += 1
|
|
if call_count["n"] == 1:
|
|
return LLMResponse(
|
|
content="thinking",
|
|
tool_calls=[ToolCallRequest(id="call_1", name="list_dir", arguments={})],
|
|
reasoning_content="hidden reasoning",
|
|
thinking_blocks=[{"type": "thinking", "thinking": "step"}],
|
|
)
|
|
captured_second_call[:] = messages
|
|
return LLMResponse(content="done", tool_calls=[])
|
|
provider.chat_with_retry = scripted_chat_with_retry
|
|
mgr = SubagentManager(provider=provider, workspace=tmp_path, bus=bus)
|
|
|
|
async def fake_execute(self, name, arguments):
|
|
return "tool result"
|
|
|
|
monkeypatch.setattr("nanobot.agent.tools.registry.ToolRegistry.execute", fake_execute)
|
|
|
|
await mgr._run_subagent("sub-1", "do task", "label", {"channel": "test", "chat_id": "c1"})
|
|
|
|
assistant_messages = [
|
|
msg for msg in captured_second_call
|
|
if msg.get("role") == "assistant" and msg.get("tool_calls")
|
|
]
|
|
assert len(assistant_messages) == 1
|
|
assert assistant_messages[0]["reasoning_content"] == "hidden reasoning"
|
|
assert assistant_messages[0]["thinking_blocks"] == [{"type": "thinking", "thinking": "step"}]
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_subagent_exec_tool_not_registered_when_disabled(self, tmp_path):
|
|
from nanobot.agent.subagent import SubagentManager
|
|
from nanobot.bus.queue import MessageBus
|
|
from nanobot.config.schema import ExecToolConfig
|
|
|
|
bus = MessageBus()
|
|
provider = MagicMock()
|
|
provider.get_default_model.return_value = "test-model"
|
|
mgr = SubagentManager(
|
|
provider=provider,
|
|
workspace=tmp_path,
|
|
bus=bus,
|
|
exec_config=ExecToolConfig(enable=False),
|
|
)
|
|
mgr._announce_result = AsyncMock()
|
|
|
|
async def fake_run(spec):
|
|
assert spec.tools.get("exec") is None
|
|
return SimpleNamespace(
|
|
stop_reason="done",
|
|
final_content="done",
|
|
error=None,
|
|
tool_events=[],
|
|
)
|
|
|
|
mgr.runner.run = AsyncMock(side_effect=fake_run)
|
|
|
|
await mgr._run_subagent("sub-1", "do task", "label", {"channel": "test", "chat_id": "c1"})
|
|
|
|
mgr.runner.run.assert_awaited_once()
|
|
mgr._announce_result.assert_awaited_once()
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_subagent_announces_error_when_tool_execution_fails(self, monkeypatch, tmp_path):
|
|
from nanobot.agent.subagent import SubagentManager
|
|
from nanobot.bus.queue import MessageBus
|
|
from nanobot.providers.base import LLMResponse, ToolCallRequest
|
|
|
|
bus = MessageBus()
|
|
provider = MagicMock()
|
|
provider.get_default_model.return_value = "test-model"
|
|
provider.chat_with_retry = AsyncMock(return_value=LLMResponse(
|
|
content="thinking",
|
|
tool_calls=[ToolCallRequest(id="call_1", name="list_dir", arguments={})],
|
|
))
|
|
mgr = SubagentManager(provider=provider, workspace=tmp_path, bus=bus)
|
|
mgr._announce_result = AsyncMock()
|
|
|
|
calls = {"n": 0}
|
|
|
|
async def fake_execute(self, name, arguments):
|
|
calls["n"] += 1
|
|
if calls["n"] == 1:
|
|
return "first result"
|
|
raise RuntimeError("boom")
|
|
|
|
monkeypatch.setattr("nanobot.agent.tools.registry.ToolRegistry.execute", fake_execute)
|
|
|
|
await mgr._run_subagent("sub-1", "do task", "label", {"channel": "test", "chat_id": "c1"})
|
|
|
|
mgr._announce_result.assert_awaited_once()
|
|
args = mgr._announce_result.await_args.args
|
|
assert "Completed steps:" in args[3]
|
|
assert "- list_dir: first result" in args[3]
|
|
assert "Failure:" in args[3]
|
|
assert "- list_dir: boom" in args[3]
|
|
assert args[5] == "error"
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_cancel_by_session_cancels_running_subagent_tool(self, monkeypatch, tmp_path):
|
|
from nanobot.agent.subagent import SubagentManager
|
|
from nanobot.bus.queue import MessageBus
|
|
from nanobot.providers.base import LLMResponse, ToolCallRequest
|
|
|
|
bus = MessageBus()
|
|
provider = MagicMock()
|
|
provider.get_default_model.return_value = "test-model"
|
|
provider.chat_with_retry = AsyncMock(return_value=LLMResponse(
|
|
content="thinking",
|
|
tool_calls=[ToolCallRequest(id="call_1", name="list_dir", arguments={})],
|
|
))
|
|
mgr = SubagentManager(provider=provider, workspace=tmp_path, bus=bus)
|
|
mgr._announce_result = AsyncMock()
|
|
|
|
started = asyncio.Event()
|
|
cancelled = asyncio.Event()
|
|
|
|
async def fake_execute(self, name, arguments):
|
|
started.set()
|
|
try:
|
|
await asyncio.sleep(60)
|
|
except asyncio.CancelledError:
|
|
cancelled.set()
|
|
raise
|
|
|
|
monkeypatch.setattr("nanobot.agent.tools.registry.ToolRegistry.execute", fake_execute)
|
|
|
|
task = asyncio.create_task(
|
|
mgr._run_subagent("sub-1", "do task", "label", {"channel": "test", "chat_id": "c1"})
|
|
)
|
|
mgr._running_tasks["sub-1"] = task
|
|
mgr._session_tasks["test:c1"] = {"sub-1"}
|
|
|
|
await started.wait()
|
|
|
|
count = await mgr.cancel_by_session("test:c1")
|
|
|
|
assert count == 1
|
|
assert cancelled.is_set()
|
|
assert task.cancelled()
|
|
mgr._announce_result.assert_not_awaited()
|