Robot_Arm/ml/selftest_proc.py

"""本机自检的进程部分（2026-10-18 第七轮，遗留 C-5：Windows 生命周期从未实测）。由 ml/selftest.sh 调用。
  tree   ：按控制台同一套标志（Windows: CREATE_NEW_PROCESS_GROUP|CREATE_NO_WINDOW；POSIX: 新会话）起 bash → python + node 两个孙进程，
           再用控制台同一套停止方法（Windows: taskkill /T /F；POSIX: 按会话 TERM）结束，检查孙进程是否全部消失。
  detach ：起一个"启动器"进程，它按同一标志拉起子树后立刻退出，检查子树是否还活着（等价于关掉控制台黑窗口后训练是否继续）。
输出一行 JSON：{"tree_killed": bool, "survive_parent_exit": bool, ...}"""
import json, os, subprocess, sys, time, tempfile, shutil

ROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
sys.path.insert(0, ROOT)
from ml.monitor import find_bash, kill_session   # noqa: E402

FLAGS = {'creationflags': subprocess.CREATE_NEW_PROCESS_GROUP | 0x08000000} if os.name == 'nt' else {'start_new_session': True}


def alive(pid):
    if os.name == 'nt':
        # 中文 Windows 的 tasklist 表头是 GBK，text=True 会让读线程解码崩掉（stdout 变 None）→ 按字节读再容错解码
        r = subprocess.run(['tasklist', '/FI', f'PID eq {pid}', '/NH'], capture_output=True, text=True, errors='replace')
        return str(pid) in (r.stdout or '')
    try: os.kill(pid, 0); return True
    except OSError: return False


def tree_cmd(d):
    py = sys.executable.replace('\\', '/'); dd = d.replace('\\', '/')
    return (f'"{py}" -c "import os,time;open(\'{dd}/p.pid\',\'w\').write(str(os.getpid()));time.sleep(300)" & '
            f'node -e "require(\'fs\').writeFileSync(\'{dd}/n.pid\',String(process.pid));setInterval(()=>{{}},1000)" & wait')


WAITERR = ['']


def wait_pids(d, t=20):
    for _ in range(t * 4):
        try: return int(open(os.path.join(d, 'p.pid')).read()), int(open(os.path.join(d, 'n.pid')).read())
        except Exception as e: WAITERR[0] = type(e).__name__ + ': ' + str(e)[:90]; time.sleep(0.25)
    return None, None      # 起不来时把最后一次异常带进结果，别让 tree_started=false 变成没有原因的失败


def main():
    bash = find_bash(); out = {'os': os.name, 'bash': bash}
    if not bash: out['error'] = '找不到 bash'; print(json.dumps(out, ensure_ascii=False)); return
    # tree
    d = tempfile.mkdtemp(prefix='st_tree_')
    p = subprocess.Popen([bash, '-c', tree_cmd(d)], stdin=subprocess.DEVNULL, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, **FLAGS)
    pp, pn = wait_pids(d)
    out['tree_started'] = pp is not None and pn is not None
    if out['tree_started']:
        if os.name == 'nt': subprocess.run(['taskkill', '/T', '/F', '/PID', str(p.pid)], capture_output=True)
        else: kill_session(p.pid)
        time.sleep(3)
        out['tree_left'] = {'python': alive(pp), 'node': alive(pn)}
        out['tree_killed'] = not any(out['tree_left'].values())
        for x in (pp, pn):   # 清场
            if alive(x):
                if os.name == 'nt': subprocess.run(['taskkill', '/F', '/PID', str(x)], capture_output=True)
                else: os.kill(x, 9)
    shutil.rmtree(d, ignore_errors=True)
    # detach：启动器拉起子树后立即退出
    d = tempfile.mkdtemp(prefix='st_det_')
    launcher = ('import subprocess,sys;' f'f={FLAGS!r};' 'subprocess.Popen([sys.argv[1],"-c",sys.argv[2]],stdin=subprocess.DEVNULL,stdout=subprocess.DEVNULL,stderr=subprocess.DEVNULL,**f)')
    subprocess.run([sys.executable, '-c', launcher, bash, tree_cmd(d)], timeout=30)
    pp, pn = wait_pids(d)
    time.sleep(3)
    out['survive_parent_exit'] = bool(pp and pn and alive(pp) and alive(pn))
    for x in (pp, pn):
        if x and alive(x):
            if os.name == 'nt': subprocess.run(['taskkill', '/F', '/PID', str(x)], capture_output=True)
            else: os.kill(x, 9)
    shutil.rmtree(d, ignore_errors=True)
    print(json.dumps(out, ensure_ascii=False))


if __name__ == '__main__':
    main()