fix(shell): reap zombie processes on all subprocess exit paths

The previous fix (dbcc7cb5) only added os.waitpid() to _kill_process(),
covering the timeout/cancel path of one-shot exec. Zombies continued to
accumulate because several other exit paths never reaped children:

- _ExecSession.kill(): sent SIGKILL + process.wait(5s) but had no
  os.waitpid() fallback if the wait timed out
- ExecTool.execute() generic exception handler: leaked the subprocess
  if communicate() raised an unexpected error
- Normal completion paths: relied entirely on asyncio's child-watcher,
  which can miss exits inside Docker containers (pidfd/SIGCHLD gaps)

Changes:
- Extract _reap_pid() helper for consistent, safe os.waitpid(WNOHANG)
- Add _reap_pid() fallback to _ExecSession.kill() via try/finally
- Add _reap_pid() safety-net after normal process exit in both
  ExecTool.execute() and _ExecSession.poll()
- Kill + reap subprocess in the generic except Exception handler
- Add periodic zombie reaper background task (every 30s) in the
  gateway as a last line of defense
This commit is contained in:
Eric Yang
2026-07-10 20:19:44 +08:00
committed by Xubin Ren
parent d32f8961b1
commit c9e014fdea
3 changed files with 70 additions and 7 deletions
+12 -2
View File
@@ -3,6 +3,7 @@
from __future__ import annotations
import asyncio
import os
import time
import uuid
from contextlib import suppress
@@ -148,6 +149,9 @@ class _ExecSession:
asyncio.gather(self._stdout_task, self._stderr_task),
timeout=2.0,
)
# Safety-net reap after normal exit.
from nanobot.agent.tools.shell import _reap_pid
_reap_pid(self.process.pid)
elif yield_time_ms > 0:
await self._wait_for_buffered_output()
@@ -171,8 +175,14 @@ class _ExecSession:
if self.process.returncode is not None:
return
self.process.kill()
with suppress(asyncio.TimeoutError):
await asyncio.wait_for(self.process.wait(), timeout=5.0)
try:
with suppress(asyncio.TimeoutError):
await asyncio.wait_for(self.process.wait(), timeout=5.0)
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)
async def _wait_for_buffered_output(self) -> None:
deadline = time.monotonic() + OUTPUT_DRAIN_GRACE_S
+29 -5
View File
@@ -41,6 +41,24 @@ from nanobot.security.workspace_policy import is_path_within
_IS_WINDOWS = sys.platform == "win32"
def _reap_pid(pid: int) -> None:
"""Best-effort ``waitpid`` to reap a child and prevent zombies.
Call this after killing or after normal completion of any subprocess
as a safety net — asyncio's child-watcher *should* have reaped it,
but in containers / edge-cases it sometimes doesn't.
"""
if _IS_WINDOWS:
return
try:
os.waitpid(pid, os.WNOHANG)
except (ProcessLookupError, ChildProcessError):
# Already reaped, or not our child — both are fine.
pass
except OSError as exc:
logger.debug("_reap_pid({}): {}", pid, exc)
# Policy note appended to recoverable workspace-boundary guard errors.
_WORKSPACE_BOUNDARY_NOTE = (
"\n\nNote: this is a hard policy boundary, not a transient failure. "
@@ -283,6 +301,7 @@ class ExecTool(Tool):
if yield_time_ms is not None:
return await self._execute_session(prepared, yield_time_ms, max_output_chars)
process: asyncio.subprocess.Process | None = None
try:
process = await self._spawn(
prepared.command,
@@ -304,6 +323,11 @@ class ExecTool(Tool):
await self._kill_process(process)
raise
# Safety-net reap: asyncio *should* have reaped the child via
# communicate(), but in containers the child-watcher sometimes
# misses it, leaving a zombie.
_reap_pid(process.pid)
output_parts = []
if stdout:
@@ -330,6 +354,10 @@ class ExecTool(Tool):
return result
except Exception as e:
# Kill and reap the child if it was spawned but an unexpected
# error prevented communicate() from completing.
if process is not None:
await self._kill_process(process)
return ToolResult.error(f"Error executing command: {str(e)}")
async def _execute_session(
@@ -604,11 +632,7 @@ class ExecTool(Tool):
with suppress(asyncio.TimeoutError):
await asyncio.wait_for(process.wait(), timeout=5.0)
finally:
if not _IS_WINDOWS:
try:
os.waitpid(process.pid, os.WNOHANG)
except (ProcessLookupError, ChildProcessError) as e:
logger.debug("Process already reaped or not found: {}", e)
_reap_pid(process.pid)
def _build_env(self) -> dict[str, str]:
"""Build a minimal environment for subprocess execution.
+29
View File
@@ -201,6 +201,7 @@ app = typer.Typer(
)
console = Console()
_IS_WINDOWS = sys.platform == "win32"
EXIT_COMMANDS = {"exit", "quit", "/exit", "/quit", ":q"}
_REASONING_SENTENCE_ENDINGS = (".", "!", "?", "", "", "")
_REASONING_FLUSH_CHARS = 60
@@ -1695,6 +1696,29 @@ def _run_gateway(
else:
console.print("[yellow]✗[/yellow] Heartbeat: disabled")
async def _zombie_reaper() -> None:
"""Periodically reap zombie child processes.
asyncio's child-watcher *should* reap all children, but inside
Docker containers the pidfd / SIGCHLD mechanism can miss exits.
This task runs every 30 s and calls ``os.waitpid(-1, WNOHANG)``
in a loop to collect any zombies that slipped through.
"""
_INTERVAL = 30
while True:
await asyncio.sleep(_INTERVAL)
reaped = 0
while True:
try:
pid, _ = os.waitpid(-1, os.WNOHANG)
if pid == 0:
break # no more zombie children
reaped += 1
except ChildProcessError:
break # no child processes at all
if reaped:
logger.info("Zombie reaper: reaped {} defunct child process(es)", reaped)
async def _health_server(host: str, health_port: int):
"""Lightweight HTTP health endpoint on the gateway port."""
import json as _json
@@ -1820,6 +1844,11 @@ def _run_gateway(
name="nanobot-local-triggers",
),
]
if not _IS_WINDOWS:
tasks.append(asyncio.create_task(
_zombie_reaper(),
name="nanobot-zombie-reaper",
))
if health_server_enabled:
tasks.append(asyncio.create_task(
_health_server(config.gateway.host, port),