fix(exec): clean up sessions on shutdown
This commit is contained in:
+16
-2
@@ -1277,11 +1277,25 @@ class AgentLoop:
|
||||
await self._publish_next_deferred_automation_turn(session_key)
|
||||
|
||||
async def close_mcp(self) -> None:
|
||||
"""Drain pending background archives, then close MCP connections."""
|
||||
"""Drain background work, stop exec sessions, then close MCP connections."""
|
||||
if self._background_tasks:
|
||||
await asyncio.gather(*self._background_tasks, return_exceptions=True)
|
||||
self._background_tasks.clear()
|
||||
await agent_context.close_mcp(self)
|
||||
errors: list[BaseException] = []
|
||||
cleanup_steps = (
|
||||
self.subagents.close,
|
||||
self._exec_session_manager.close_all,
|
||||
lambda: agent_context.close_mcp(self),
|
||||
)
|
||||
for cleanup in cleanup_steps:
|
||||
try:
|
||||
await cleanup()
|
||||
except BaseException as exc:
|
||||
errors.append(exc)
|
||||
if len(errors) == 1:
|
||||
raise errors[0]
|
||||
if errors:
|
||||
raise BaseExceptionGroup("failed to close agent resources", errors)
|
||||
|
||||
def _schedule_background(self, coro) -> None:
|
||||
"""Schedule a coroutine as a tracked background task (drained on shutdown)."""
|
||||
|
||||
@@ -459,6 +459,15 @@ class SubagentManager:
|
||||
await asyncio.gather(*tasks, return_exceptions=True)
|
||||
return len(tasks)
|
||||
|
||||
async def close(self) -> None:
|
||||
"""Cancel running subagents and close their shared exec sessions."""
|
||||
tasks = [task for task in self._running_tasks.values() if not task.done()]
|
||||
for task in tasks:
|
||||
task.cancel()
|
||||
if tasks:
|
||||
await asyncio.gather(*tasks, return_exceptions=True)
|
||||
await self._exec_session_manager.close_all()
|
||||
|
||||
def get_running_count(self) -> int:
|
||||
"""Return the number of currently running subagents."""
|
||||
return len(self._running_tasks)
|
||||
|
||||
@@ -61,12 +61,14 @@ class _ExecSession:
|
||||
cwd: str,
|
||||
timeout: int | None,
|
||||
owner_session_key: str | None = None,
|
||||
process_tree: bool = False,
|
||||
) -> None:
|
||||
self.session_id = session_id
|
||||
self.process = process
|
||||
self.command = command
|
||||
self.cwd = cwd
|
||||
self.owner_session_key = owner_session_key
|
||||
self._process_tree = process_tree
|
||||
self.started_at = time.monotonic()
|
||||
# timeout None/0 means no limit; an infinite deadline is never reached.
|
||||
self.deadline = time.monotonic() + timeout if timeout else float("inf")
|
||||
@@ -171,17 +173,23 @@ class _ExecSession:
|
||||
)
|
||||
|
||||
async def kill(self) -> None:
|
||||
if self.process.returncode is not None:
|
||||
return
|
||||
self.process.kill()
|
||||
from nanobot.agent.tools.shell import ExecTool
|
||||
|
||||
try:
|
||||
with suppress(asyncio.TimeoutError):
|
||||
await asyncio.wait_for(self.process.wait(), timeout=5.0)
|
||||
if self._process_tree:
|
||||
await ExecTool._kill_process_tree(self.process)
|
||||
else:
|
||||
await ExecTool._kill_process(self.process)
|
||||
finally:
|
||||
# Safety-net waitpid — prevent zombie if asyncio's child watcher
|
||||
# did not reap the process (common in containers).
|
||||
from nanobot.agent.tools.shell import _reap_pid
|
||||
_reap_pid(self.process.pid)
|
||||
with suppress(asyncio.TimeoutError):
|
||||
await asyncio.wait_for(
|
||||
asyncio.gather(
|
||||
self._stdout_task,
|
||||
self._stderr_task,
|
||||
return_exceptions=True,
|
||||
),
|
||||
timeout=2.0,
|
||||
)
|
||||
|
||||
async def _wait_for_buffered_output(self) -> None:
|
||||
deadline = time.monotonic() + OUTPUT_DRAIN_GRACE_S
|
||||
@@ -198,6 +206,7 @@ class ExecSessionManager:
|
||||
self.idle_timeout = idle_timeout
|
||||
self._sessions: dict[str, _ExecSession] = {}
|
||||
self._lock = asyncio.Lock()
|
||||
self._closed = False
|
||||
|
||||
async def start(
|
||||
self,
|
||||
@@ -213,6 +222,8 @@ class ExecSessionManager:
|
||||
owner_session_key: str | None = None,
|
||||
) -> tuple[str, _SessionPoll]:
|
||||
async with self._lock:
|
||||
if self._closed:
|
||||
raise RuntimeError("exec session manager is closed")
|
||||
await self._cleanup_locked()
|
||||
if len(self._sessions) >= self.max_sessions:
|
||||
raise RuntimeError(f"maximum exec sessions reached ({self.max_sessions})")
|
||||
@@ -225,6 +236,7 @@ class ExecSessionManager:
|
||||
cwd=cwd,
|
||||
timeout=timeout,
|
||||
owner_session_key=owner_session_key,
|
||||
process_tree=True,
|
||||
)
|
||||
self._sessions[session_id] = session
|
||||
|
||||
@@ -295,6 +307,33 @@ class ExecSessionManager:
|
||||
if session.owner_session_key == owner_session_key
|
||||
]
|
||||
|
||||
async def close_all(self) -> int:
|
||||
"""Terminate and remove all active sessions during shutdown."""
|
||||
async with self._lock:
|
||||
self._closed = True
|
||||
sessions = list(self._sessions.values())
|
||||
self._sessions.clear()
|
||||
results = await asyncio.gather(
|
||||
*(session.kill() for session in sessions),
|
||||
return_exceptions=True,
|
||||
)
|
||||
failures = [
|
||||
(session, result)
|
||||
for session, result in zip(sessions, results, strict=True)
|
||||
if isinstance(result, BaseException)
|
||||
]
|
||||
if failures:
|
||||
async with self._lock:
|
||||
for session, _ in failures:
|
||||
self._sessions[session.session_id] = session
|
||||
if len(failures) == 1:
|
||||
raise failures[0][1]
|
||||
raise BaseExceptionGroup(
|
||||
"failed to close exec sessions",
|
||||
[result for _, result in failures],
|
||||
)
|
||||
return len(sessions)
|
||||
|
||||
async def _cleanup_locked(self) -> None:
|
||||
now = time.monotonic()
|
||||
stale = [
|
||||
@@ -319,6 +358,7 @@ class ExecSessionManager:
|
||||
return await ExecTool._spawn(
|
||||
command, cwd, env, shell_program, login,
|
||||
stdin=asyncio.subprocess.PIPE,
|
||||
process_tree=True,
|
||||
)
|
||||
|
||||
|
||||
|
||||
@@ -6,6 +6,8 @@ import asyncio
|
||||
import os
|
||||
import re
|
||||
import shutil
|
||||
import signal
|
||||
import subprocess
|
||||
import sys
|
||||
from contextlib import suppress
|
||||
from dataclasses import dataclass
|
||||
@@ -516,6 +518,7 @@ class ExecTool(Tool):
|
||||
login: bool = False,
|
||||
*,
|
||||
stdin: int = asyncio.subprocess.DEVNULL,
|
||||
process_tree: bool = False,
|
||||
) -> asyncio.subprocess.Process:
|
||||
"""Launch *command* in a platform-appropriate shell."""
|
||||
if _IS_WINDOWS:
|
||||
@@ -563,6 +566,7 @@ class ExecTool(Tool):
|
||||
stderr=asyncio.subprocess.PIPE,
|
||||
cwd=cwd,
|
||||
env=env,
|
||||
**({"start_new_session": True} if process_tree else {}),
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
@@ -655,6 +659,39 @@ class ExecTool(Tool):
|
||||
finally:
|
||||
_reap_pid(process.pid)
|
||||
|
||||
@staticmethod
|
||||
async def _kill_process_tree(process: asyncio.subprocess.Process) -> None:
|
||||
"""Kill a session process and descendants, then reap the root process."""
|
||||
if process.returncode is not None:
|
||||
_reap_pid(process.pid)
|
||||
return
|
||||
try:
|
||||
if _IS_WINDOWS:
|
||||
with suppress(OSError, asyncio.TimeoutError):
|
||||
await asyncio.wait_for(
|
||||
asyncio.to_thread(
|
||||
subprocess.run,
|
||||
["taskkill", "/PID", str(process.pid), "/T", "/F"],
|
||||
check=False,
|
||||
stdout=subprocess.DEVNULL,
|
||||
stderr=subprocess.DEVNULL,
|
||||
),
|
||||
timeout=5.0,
|
||||
)
|
||||
else:
|
||||
try:
|
||||
os.killpg(process.pid, signal.SIGKILL)
|
||||
except (ProcessLookupError, PermissionError):
|
||||
pass
|
||||
|
||||
if process.returncode is None:
|
||||
with suppress(ProcessLookupError):
|
||||
process.kill()
|
||||
with suppress(asyncio.TimeoutError):
|
||||
await asyncio.wait_for(process.wait(), timeout=5.0)
|
||||
finally:
|
||||
_reap_pid(process.pid)
|
||||
|
||||
def _build_env(self) -> dict[str, str]:
|
||||
"""Build a minimal environment for subprocess execution.
|
||||
|
||||
|
||||
@@ -37,6 +37,7 @@ def _make_loop(tmp_path):
|
||||
patch("nanobot.agent.loop.SessionManager"), \
|
||||
patch("nanobot.agent.loop.SubagentManager") as mock_sub_mgr:
|
||||
mock_sub_mgr.return_value.cancel_by_session = AsyncMock(return_value=0)
|
||||
mock_sub_mgr.return_value.close = AsyncMock()
|
||||
loop = AgentLoop(bus=bus, provider=provider, workspace=tmp_path)
|
||||
return loop
|
||||
|
||||
|
||||
@@ -65,6 +65,24 @@ async def _drain_subagent_tasks(sm: SubagentManager) -> None:
|
||||
await asyncio.sleep(0)
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_close_cancels_tasks_before_closing_exec_sessions(tmp_path):
|
||||
sm = _manager(tmp_path)
|
||||
task = asyncio.create_task(asyncio.Event().wait())
|
||||
sm._running_tasks["t1"] = task
|
||||
|
||||
async def close_exec_sessions() -> int:
|
||||
assert task.done()
|
||||
return 0
|
||||
|
||||
sm._exec_session_manager.close_all = AsyncMock(side_effect=close_exec_sessions)
|
||||
|
||||
await sm.close()
|
||||
|
||||
assert task.cancelled()
|
||||
sm._exec_session_manager.close_all.assert_awaited_once()
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# SubagentStatus defaults
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
@@ -28,7 +28,8 @@ def _make_loop():
|
||||
|
||||
with patch("nanobot.agent.loop.ContextBuilder"), \
|
||||
patch("nanobot.agent.loop.SessionManager"), \
|
||||
patch("nanobot.agent.loop.SubagentManager"):
|
||||
patch("nanobot.agent.loop.SubagentManager") as mock_sub_mgr:
|
||||
mock_sub_mgr.return_value.close = AsyncMock()
|
||||
loop = AgentLoop(bus=bus, provider=provider, workspace=workspace)
|
||||
return loop, bus
|
||||
|
||||
|
||||
@@ -114,6 +114,22 @@ class TestSpawnUnix:
|
||||
kwargs = mock_exec.call_args[1]
|
||||
assert kwargs["stdin"] == asyncio.subprocess.DEVNULL
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_process_tree_starts_new_session(self):
|
||||
with (
|
||||
patch("nanobot.agent.tools.shell._IS_WINDOWS", False),
|
||||
patch("asyncio.create_subprocess_exec", new_callable=AsyncMock) as mock_exec,
|
||||
):
|
||||
mock_exec.return_value = AsyncMock()
|
||||
await ExecTool._spawn(
|
||||
"echo hi",
|
||||
"/tmp",
|
||||
{"HOME": "/tmp"},
|
||||
process_tree=True,
|
||||
)
|
||||
|
||||
assert mock_exec.call_args.kwargs["start_new_session"] is True
|
||||
|
||||
|
||||
class TestSpawnWindows:
|
||||
|
||||
|
||||
@@ -1,12 +1,19 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import base64
|
||||
import re
|
||||
import shlex
|
||||
import subprocess
|
||||
import sys
|
||||
import time
|
||||
from types import SimpleNamespace
|
||||
from unittest.mock import AsyncMock
|
||||
|
||||
import pytest
|
||||
|
||||
from nanobot.agent import context as agent_context
|
||||
from nanobot.agent.loop import AgentLoop
|
||||
from nanobot.agent.tools.context import RequestContext, bind_request_context, reset_request_context
|
||||
from nanobot.agent.tools.exec_session import (
|
||||
ExecSessionManager,
|
||||
@@ -454,3 +461,182 @@ def test_list_exec_sessions_reports_empty_state():
|
||||
result = asyncio.run(ListExecSessionsTool(manager=ExecSessionManager()).execute())
|
||||
|
||||
assert result == "No active exec sessions."
|
||||
|
||||
|
||||
def test_exec_session_manager_close_all_terminates_active_sessions(tmp_path):
|
||||
async def run() -> None:
|
||||
manager = ExecSessionManager()
|
||||
tool = ExecTool(working_dir=str(tmp_path), timeout=30, session_manager=manager)
|
||||
initial = await tool.execute(
|
||||
command=_waiting_shell_command("ready"),
|
||||
yield_time_ms=100,
|
||||
)
|
||||
sid = _session_id(initial)
|
||||
process = manager._sessions[sid].process
|
||||
assert process.returncode is None
|
||||
|
||||
closed = await manager.close_all()
|
||||
|
||||
assert closed == 1
|
||||
assert process.returncode is not None
|
||||
assert manager._sessions == {}
|
||||
assert await manager.close_all() == 0
|
||||
|
||||
asyncio.run(run())
|
||||
|
||||
|
||||
def test_exec_session_manager_shutdown_terminates_child_processes(tmp_path):
|
||||
async def run() -> None:
|
||||
marker = tmp_path / "orphaned-child.txt"
|
||||
child_code = (
|
||||
"import pathlib,time; time.sleep(2); "
|
||||
f"pathlib.Path({str(marker)!r}).write_text('alive')"
|
||||
)
|
||||
child_payload = base64.b64encode(child_code.encode()).decode()
|
||||
parent_code = (
|
||||
"import base64,subprocess,sys,time; "
|
||||
f"child=base64.b64decode('{child_payload}').decode(); "
|
||||
"subprocess.Popen([sys.executable, '-c', child]); "
|
||||
"print('ready', flush=True); time.sleep(4)"
|
||||
)
|
||||
manager = ExecSessionManager()
|
||||
tool = ExecTool(working_dir=str(tmp_path), timeout=30, session_manager=manager)
|
||||
initial = await tool.execute(command=_python_command(parent_code), yield_time_ms=500)
|
||||
assert "ready" in initial
|
||||
assert "Process running" in initial
|
||||
|
||||
await manager.close_all()
|
||||
await asyncio.sleep(2.3)
|
||||
|
||||
assert not marker.exists()
|
||||
|
||||
asyncio.run(run())
|
||||
|
||||
|
||||
def test_exec_session_manager_rejects_new_sessions_after_shutdown(tmp_path):
|
||||
async def run() -> str:
|
||||
manager = ExecSessionManager()
|
||||
await manager.close_all()
|
||||
tool = ExecTool(working_dir=str(tmp_path), timeout=5, session_manager=manager)
|
||||
return await tool.execute(command="echo should-not-run", yield_time_ms=0)
|
||||
|
||||
result = asyncio.run(run())
|
||||
|
||||
assert result == "Error executing command: exec session manager is closed"
|
||||
|
||||
|
||||
def test_exec_session_manager_retains_and_aggregates_failed_cleanup():
|
||||
async def run() -> None:
|
||||
manager = ExecSessionManager()
|
||||
first = SimpleNamespace(
|
||||
session_id="first",
|
||||
kill=AsyncMock(side_effect=OSError("first failed")),
|
||||
)
|
||||
second = SimpleNamespace(
|
||||
session_id="second",
|
||||
kill=AsyncMock(side_effect=RuntimeError("second failed")),
|
||||
)
|
||||
manager._sessions = {first.session_id: first, second.session_id: second}
|
||||
|
||||
with pytest.raises(ExceptionGroup) as exc_info:
|
||||
await manager.close_all()
|
||||
|
||||
assert len(exc_info.value.exceptions) == 2
|
||||
assert manager._sessions == {first.session_id: first, second.session_id: second}
|
||||
first.kill.assert_awaited_once()
|
||||
second.kill.assert_awaited_once()
|
||||
|
||||
first.kill.side_effect = None
|
||||
second.kill.side_effect = None
|
||||
assert await manager.close_all() == 2
|
||||
assert manager._sessions == {}
|
||||
|
||||
asyncio.run(run())
|
||||
|
||||
|
||||
def test_exec_session_manager_preserves_single_cleanup_error():
|
||||
async def run() -> None:
|
||||
manager = ExecSessionManager()
|
||||
session = SimpleNamespace(
|
||||
session_id="failed",
|
||||
kill=AsyncMock(side_effect=OSError("cleanup failed")),
|
||||
)
|
||||
manager._sessions = {session.session_id: session}
|
||||
|
||||
with pytest.raises(OSError, match="cleanup failed"):
|
||||
await manager.close_all()
|
||||
|
||||
assert manager._sessions == {session.session_id: session}
|
||||
|
||||
asyncio.run(run())
|
||||
|
||||
|
||||
def test_agent_loop_shutdown_closes_exec_sessions(tmp_path, monkeypatch):
|
||||
async def run() -> None:
|
||||
manager = ExecSessionManager()
|
||||
tool = ExecTool(working_dir=str(tmp_path), timeout=30, session_manager=manager)
|
||||
initial = await tool.execute(
|
||||
command=_waiting_shell_command("ready"),
|
||||
yield_time_ms=100,
|
||||
)
|
||||
sid = _session_id(initial)
|
||||
process = manager._sessions[sid].process
|
||||
|
||||
monkeypatch.setattr(agent_context, "close_mcp", lambda _state: asyncio.sleep(0))
|
||||
loop = object.__new__(AgentLoop)
|
||||
loop._background_tasks = []
|
||||
loop._exec_session_manager = manager
|
||||
loop.subagents = SimpleNamespace(close=AsyncMock())
|
||||
|
||||
await loop.close_mcp()
|
||||
await loop.close_mcp()
|
||||
|
||||
assert process.returncode is not None
|
||||
assert manager._sessions == {}
|
||||
assert loop.subagents.close.await_count == 2
|
||||
|
||||
asyncio.run(run())
|
||||
|
||||
|
||||
def test_agent_loop_shutdown_attempts_all_cleanup_after_errors(monkeypatch):
|
||||
async def run() -> None:
|
||||
loop = object.__new__(AgentLoop)
|
||||
loop._background_tasks = []
|
||||
loop.subagents = SimpleNamespace(
|
||||
close=AsyncMock(side_effect=RuntimeError("subagent cleanup failed")),
|
||||
)
|
||||
loop._exec_session_manager = SimpleNamespace(
|
||||
close_all=AsyncMock(side_effect=OSError("exec cleanup failed")),
|
||||
)
|
||||
close_mcp = AsyncMock()
|
||||
monkeypatch.setattr(agent_context, "close_mcp", close_mcp)
|
||||
|
||||
with pytest.raises(BaseExceptionGroup) as exc_info:
|
||||
await loop.close_mcp()
|
||||
|
||||
assert len(exc_info.value.exceptions) == 2
|
||||
loop.subagents.close.assert_awaited_once()
|
||||
loop._exec_session_manager.close_all.assert_awaited_once()
|
||||
close_mcp.assert_awaited_once_with(loop)
|
||||
|
||||
asyncio.run(run())
|
||||
|
||||
|
||||
def test_agent_loop_shutdown_preserves_single_cleanup_error(monkeypatch):
|
||||
async def run() -> None:
|
||||
loop = object.__new__(AgentLoop)
|
||||
loop._background_tasks = []
|
||||
loop.subagents = SimpleNamespace(
|
||||
close=AsyncMock(side_effect=RuntimeError("subagent cleanup failed")),
|
||||
)
|
||||
loop._exec_session_manager = SimpleNamespace(close_all=AsyncMock())
|
||||
close_mcp = AsyncMock()
|
||||
monkeypatch.setattr(agent_context, "close_mcp", close_mcp)
|
||||
|
||||
with pytest.raises(RuntimeError, match="subagent cleanup failed"):
|
||||
await loop.close_mcp()
|
||||
|
||||
loop._exec_session_manager.close_all.assert_awaited_once()
|
||||
close_mcp.assert_awaited_once_with(loop)
|
||||
|
||||
asyncio.run(run())
|
||||
|
||||
@@ -211,6 +211,62 @@ async def test_exec_session_kill_reaps():
|
||||
await asyncio.gather(session._stdout_task, session._stderr_task, return_exceptions=True)
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_exec_session_kill_reaps_if_process_exits_before_kill():
|
||||
process = _mock_session_process(pid=2002, returncode=None)
|
||||
process.kill.side_effect = ProcessLookupError("raced exit")
|
||||
session = _ExecSession(
|
||||
session_id="raced",
|
||||
process=process,
|
||||
command="sleep 1",
|
||||
cwd="/tmp",
|
||||
timeout=30,
|
||||
owner_session_key=None,
|
||||
)
|
||||
try:
|
||||
with patch("nanobot.agent.tools.shell._reap_pid") as reap:
|
||||
await session.kill()
|
||||
reap.assert_called_once_with(2002)
|
||||
finally:
|
||||
await asyncio.gather(session._stdout_task, session._stderr_task, return_exceptions=True)
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_exec_session_kill_waits_for_reader_tasks():
|
||||
process = _mock_session_process(pid=2003, returncode=None)
|
||||
session = _ExecSession(
|
||||
session_id="readers",
|
||||
process=process,
|
||||
command="sleep 1",
|
||||
cwd="/tmp",
|
||||
timeout=30,
|
||||
owner_session_key=None,
|
||||
)
|
||||
await asyncio.gather(session._stdout_task, session._stderr_task)
|
||||
|
||||
release = asyncio.Event()
|
||||
|
||||
async def reader() -> None:
|
||||
await release.wait()
|
||||
|
||||
async def wait_for_process() -> int:
|
||||
release.set()
|
||||
process.returncode = -9
|
||||
return -9
|
||||
|
||||
session._stdout_task = asyncio.create_task(reader())
|
||||
session._stderr_task = asyncio.create_task(reader())
|
||||
process.wait = AsyncMock(side_effect=wait_for_process)
|
||||
try:
|
||||
await session.kill()
|
||||
|
||||
assert session._stdout_task.done()
|
||||
assert session._stderr_task.done()
|
||||
finally:
|
||||
release.set()
|
||||
await asyncio.gather(session._stdout_task, session._stderr_task)
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_exec_session_poll_reaps_after_exit():
|
||||
process = _mock_session_process(pid=2002, returncode=0)
|
||||
|
||||
Reference in New Issue
Block a user