"""Docker 沙箱执行器单测:命令构造、安全挂载、超时与取消。 运行(在 ~/workspace/codex-app-server 下): python3 -m unittest discover -s cloud/tests -p "test_docker_sandbox.py" -v 说明:全部用注入的假 docker runner,不调用真实 docker、不联网、 不跑真实模型回合;env 映射里的值只是占位假名,绝不是真实密钥。 """ import json import os import sqlite3 import subprocess import sys import tempfile import time import unittest from pathlib import Path from types import SimpleNamespace from unittest import mock try: from cloud.sandbox import DockerExecutor from cloud.server import init_db from cloud.worker import Worker except ImportError: # discover -s cloud/tests 时把项目根目录补进 sys.path sys.path.insert(0, str(Path(__file__).resolve().parents[2])) from cloud.sandbox import DockerExecutor from cloud.server import init_db from cloud.worker import Worker def _ok_runner_factory(seen): def fake(cmd, timeout=None): seen.append(list(cmd)) return SimpleNamespace( returncode=0, stdout=json.dumps({"status": "completed", "text": "done"}), stderr="") return fake def _insert_task(db_path, task_id, prompt="do work"): now = time.time() conn = sqlite3.connect(db_path) try: conn.execute( "INSERT INTO tasks(id, project_id, prompt, status," " idempotency_key, depends_on, priority, created_by," " created_at, updated_at, last_heartbeat)" " VALUES(?, 'p1', ?, 'queued', NULL, '[]', 0, 'tester', ?, ?, NULL)", (task_id, prompt, now, now), ) conn.commit() finally: conn.close() def _task_status(db_path, task_id): conn = sqlite3.connect(db_path) try: row = conn.execute( "SELECT status, error_text FROM tasks WHERE id = ?", (task_id,)).fetchone() finally: conn.close() return row class DockerCommandTestCase(unittest.TestCase): def _executor(self, seen, **kwargs): kwargs.setdefault("runner", _ok_runner_factory(seen)) kwargs.setdefault("env", {"XCM_API_KEY": "placeholder-not-a-real-key"}) return DockerExecutor("/fake/host.py", **kwargs) def test_command_mounts_only_task_worktree_and_ro_code(self): seen = [] with mock.patch("cloud.sandbox.shutil.which", return_value="/usr/bin/docker"): ex = self._executor(seen) cmd = ex.build_run_command( {"id": "t1", "worktree": "/tmp/wt-t1"}, ["python3", "/app/host.py", "status", "--task", "t1"]) mounts = [cmd[i + 1] for i, a in enumerate(cmd) if a == "-v"] self.assertEqual(mounts, ["/tmp/wt-t1:/work", "/fake:/app:ro"]) # 绝不挂载宿主根目录。 self.assertNotIn("/:/work", mounts) self.assertNotIn("/:/app:ro", mounts) self.assertIn("--rm", cmd) self.assertIn("/tmp/wt-t1:/work", cmd) def test_command_resource_limits_and_non_root_user(self): seen = [] with mock.patch("cloud.sandbox.shutil.which", return_value="/usr/bin/docker"): ex = self._executor(seen, cpus="1", memory="512m", user="1000:1000") cmd = ex.build_run_command( {"id": "t1", "worktree": "/tmp/wt"}, ["echo", "hi"]) self.assertEqual(cmd[cmd.index("--cpus") + 1], "1") self.assertEqual(cmd[cmd.index("--memory") + 1], "512m") self.assertEqual(cmd[cmd.index("--user") + 1], "1000:1000") self.assertNotEqual(cmd[cmd.index("--user") + 1], "0") self.assertNotEqual(cmd[cmd.index("--user") + 1], "root") def test_command_defaults_are_2cpu_2g(self): seen = [] with mock.patch("cloud.sandbox.shutil.which", return_value="/usr/bin/docker"): ex = self._executor(seen) cmd = ex.build_run_command( {"id": "t1", "worktree": "/tmp/wt"}, ["echo", "hi"]) self.assertEqual(cmd[cmd.index("--cpus") + 1], "2") self.assertEqual(cmd[cmd.index("--memory") + 1], "2g") def test_container_name_sanitized(self): seen = [] with mock.patch("cloud.sandbox.shutil.which", return_value="/usr/bin/docker"): ex = self._executor(seen) self.assertEqual(ex.container_name({"id": "a b/c"}), "codex-a-b-c") cmd = ex.build_run_command( {"id": "a b/c", "worktree": "/tmp/wt"}, ["echo", "hi"]) self.assertIn("codex-a-b-c", cmd) self.assertEqual(cmd[cmd.index("--name") + 1], "codex-a-b-c") def test_env_name_only_no_value_in_command(self): seen = [] with mock.patch("cloud.sandbox.shutil.which", return_value="/usr/bin/docker"): ex = self._executor(seen) cmd = ex.build_run_command( {"id": "t1", "worktree": "/tmp/wt"}, ["echo", "hi"]) joined = " ".join(cmd) self.assertIn("-e", cmd) self.assertIn("XCM_API_KEY", cmd) # 值绝不出现在命令列表里(-e 只传名,docker 从宿主环境取值)。 self.assertNotIn("placeholder-not-a-real-key", joined) self.assertNotIn("placeholder-not-a-real-key=", joined) def test_missing_key_does_not_start_container(self): seen = [] with mock.patch("cloud.sandbox.shutil.which", return_value="/usr/bin/docker"): ex = DockerExecutor("/fake/host.py", runner=_ok_runner_factory(seen), env={}) with self.assertRaises(RuntimeError) as ctx: ex.dispatch_task({"id": "t1", "prompt": "hi", "worktree": "/tmp/wt"}) self.assertIn("Missing environment variable", str(ctx.exception)) self.assertEqual(seen, []) def test_missing_docker_does_not_call_runner(self): seen = [] with mock.patch("cloud.sandbox.shutil.which", return_value=None): ex = self._executor(seen) with self.assertRaises(RuntimeError) as ctx: ex.dispatch_task({"id": "t1", "prompt": "hi", "worktree": "/tmp/wt"}) self.assertIn("docker not available", str(ctx.exception)) self.assertEqual(seen, []) def test_dispatch_and_run_shapes(self): seen = [] with mock.patch("cloud.sandbox.shutil.which", return_value="/usr/bin/docker"): ex = self._executor(seen) dispatched = ex.dispatch_task( {"id": "t1", "prompt": "do it", "worktree": "/tmp/wt"}) ran = ex.run_task( {"id": "t1", "prompt": "again", "worktree": "/tmp/wt"}) self.assertEqual(dispatched["status"], "completed") self.assertEqual(dispatched["executor"], "docker") dispatch_cmd = seen[0] self.assertIn("dispatch", dispatch_cmd) self.assertIn("t1", dispatch_cmd) self.assertIn("do it", dispatch_cmd) run_cmd = seen[1] self.assertIn("run", run_cmd) self.assertIn("again", run_cmd) def test_execute_is_readonly_status_not_dispatch(self): seen = [] with mock.patch("cloud.sandbox.shutil.which", return_value="/usr/bin/docker"): ex = self._executor(seen) result = ex.execute({"id": "t1", "worktree": "/tmp/wt"}) self.assertEqual(result["status"], "completed") self.assertIn("status", seen[0]) self.assertNotIn("dispatch", seen[0]) # run 在命令里会出现 "--name" 等,但内层命令不应是 run: # 内层 host.py 命令的第一个动词是 status。 inner = seen[0][seen[0].index("codex-app-server:latest") + 1:] self.assertEqual(inner[2], "status") def test_timeout_kills_and_removes_container(self): seen = [] def fake(cmd, timeout=None): seen.append(list(cmd)) if len(cmd) > 1 and cmd[1] == "run": raise subprocess.TimeoutExpired(cmd, timeout) return SimpleNamespace(returncode=0, stdout="", stderr="") with mock.patch("cloud.sandbox.shutil.which", return_value="/usr/bin/docker"): ex = DockerExecutor("/fake/host.py", runner=fake, env={"XCM_API_KEY": "placeholder"}, timeout=5) result = ex.dispatch_task( {"id": "t9", "prompt": "slow", "worktree": "/tmp/wt"}) self.assertEqual(result["status"], "failed") self.assertIn("timeout", result["stdout"]) kinds = [(c[1], c[2]) for c in seen if len(c) > 2] self.assertIn(("kill", "codex-t9"), kinds) self.assertIn(("rm", "-f"), [(c[1], c[2]) for c in seen if len(c) > 2]) def test_timeout_keeps_partial_stdout_and_container_logs(self): # 旧超时路径只剩一句 'docker run timeout':TimeoutExpired # 自带的 partial stdout 与 kill 后抓的 docker logs 尾都 # 被丢了。新路径:先 kill 不 rm,抓 logs,再 rm。 seen = [] def fake(cmd, timeout=None): seen.append(list(cmd)) if len(cmd) > 1 and cmd[1] == "run": exc = subprocess.TimeoutExpired(cmd, timeout) exc.stdout = "partial-host-output" exc.stderr = "partial-err" raise exc if len(cmd) > 1 and cmd[1] == "logs": return SimpleNamespace(returncode=0, stdout="container-tail-log", stderr="") return SimpleNamespace(returncode=0, stdout="", stderr="") with mock.patch("cloud.sandbox.shutil.which", return_value="/usr/bin/docker"): ex = DockerExecutor("/fake/host.py", runner=fake, env={"XCM_API_KEY": "placeholder"}, timeout=5) result = ex.dispatch_task( {"id": "t10", "prompt": "slow", "worktree": "/tmp/wt"}) self.assertEqual(result["status"], "failed") self.assertIn("partial-host-output", result["stdout"]) # partial 已有内容时 stdout 优先用 partial,logs 另存字段。 self.assertEqual(result["container_log_tail"], "container-tail-log") # 顺序:kill → logs → rm,logs 必须在 rm 之前抓到。 kinds = [c[1] for c in seen if len(c) > 1] self.assertLess(kinds.index("logs"), kinds.index("rm")) def test_kill_container_calls_kill_and_rm(self): seen = [] with mock.patch("cloud.sandbox.shutil.which", return_value="/usr/bin/docker"): ex = self._executor(seen) ok = ex.kill_container({"id": "t2"}) self.assertTrue(ok) self.assertEqual([c[1] for c in seen], ["kill", "rm"]) self.assertEqual(seen[0][2], "codex-t2") self.assertEqual(seen[1][2], "-f") self.assertEqual(seen[1][3], "codex-t2") class WorkerDockerTestCase(unittest.TestCase): def setUp(self): self.tmp = tempfile.TemporaryDirectory() self.db_path = os.path.join(self.tmp.name, "control.db") init_db(self.db_path) self.env = {"XCM_API_KEY": "placeholder-not-a-real-key"} def tearDown(self): self.tmp.cleanup() def test_worker_docker_missing_fails_task_with_docker_error(self): seen = [] def fake(cmd, timeout=None): seen.append(list(cmd)) return SimpleNamespace(returncode=0, stdout="{}", stderr="") _insert_task(self.db_path, "d1", prompt="do it") with mock.patch("cloud.sandbox.shutil.which", return_value=None): ex = DockerExecutor("/fake/host.py", runner=fake, env=self.env) worker = Worker(self.db_path, "/fake/host.py", env={"XCM_API_KEY": "placeholder-not-a-real-key"}, executor=ex) result = worker.run_one() self.assertTrue(result["dispatched"]) self.assertEqual(result["status"], "failed") self.assertIn("docker", result["error"]) self.assertEqual(seen, []) status, error_text = _task_status(self.db_path, "d1") self.assertEqual(status, "failed") self.assertIn("docker", error_text) def test_worker_docker_success(self): seen = [] _insert_task(self.db_path, "d2", prompt="do it") with mock.patch("cloud.sandbox.shutil.which", return_value="/usr/bin/docker"): ex = DockerExecutor("/fake/host.py", runner=_ok_runner_factory(seen), env=self.env) worker = Worker(self.db_path, "/fake/host.py", env={"XCM_API_KEY": "placeholder-not-a-real-key"}, executor=ex) result = worker.run_one() self.assertTrue(result["dispatched"]) self.assertEqual(result["status"], "completed") self.assertEqual(result["executor"], "docker") self.assertTrue(any(c[1] == "run" for c in seen)) def test_worker_cancel_kills_docker_container(self): seen = [] _insert_task(self.db_path, "d3", prompt="do it") with mock.patch("cloud.sandbox.shutil.which", return_value="/usr/bin/docker"): ex = DockerExecutor("/fake/host.py", runner=_ok_runner_factory(seen), env=self.env) worker = Worker(self.db_path, "/fake/host.py", env={"XCM_API_KEY": "placeholder-not-a-real-key"}, executor=ex) # 模拟 dispatch 阻塞期间:worker 已把容器名记下来。 worker._running_set("d3", container="codex-d3") conn = sqlite3.connect(self.db_path) try: conn.execute( "UPDATE tasks SET status = 'running' WHERE id = 'd3'") conn.commit() finally: conn.close() self.assertTrue(worker.cancel("d3")) self.assertEqual([c[1] for c in seen], ["kill", "rm"]) status, _ = _task_status(self.db_path, "d3") self.assertEqual(status, "interrupted") if __name__ == "__main__": unittest.main() class TestDockerExtraMounts(DockerCommandTestCase): def test_extra_mounts_appended_after_base_mounts(self): with tempfile.TemporaryDirectory() as td: work = os.path.join(td, "work") os.makedirs(work) state = os.path.join(td, "host-state.json") open(state, "w").write("{}") with mock.patch("cloud.sandbox.shutil.which", return_value="/usr/bin/docker"): ex = DockerExecutor("/fake/host.py", runner=_ok_runner_factory([]), env={"XCM_API_KEY": "placeholder-not-a-real-key"}, extra_mounts=[f"{work}:/app/work", f"{state}:/app/host-state.json"]) cmd = ex.build_run_command({"id": "t1"}, ["python3", "/app/host.py", "status"]) # 基础挂载在前,额外挂载在后,且 /app/work 覆盖只读子路径 self.assertIn(f"{work}:/app/work:rw", cmd) self.assertIn(f"{state}:/app/host-state.json:rw", cmd) mounts = [cmd[i + 1] for i, a in enumerate(cmd) if a == "-v"] self.assertEqual(mounts[1], "/fake:/app:ro") self.assertIn(f"{work}:/app/work:rw", mounts) self.assertLess(mounts.index("/fake:/app:ro"), mounts.index(f"{work}:/app/work:rw")) def test_extra_mounts_reject_dangerous_paths(self): with self.assertRaises(ValueError): DockerExecutor("/fake/host.py", extra_mounts=["/: /x"]) with self.assertRaises(ValueError): DockerExecutor("/fake/host.py", extra_mounts=["/etc/codex-app-server/env:/x"]) with self.assertRaises(ValueError): DockerExecutor("/fake/host.py", extra_mounts=["/tmp:/app"]) with self.assertRaises(ValueError): DockerExecutor("/fake/host.py", extra_mounts=["/nonexistent-xyz:/x"]) class TestDockerDefaultRunnerEnv(unittest.TestCase): def test_env_merged_not_replaced(self): from cloud.sandbox import _docker_default_runner out = _docker_default_runner( ["python3", "-c", "import os,sys;sys.stdout.write(" "os.environ.get('PROBE_X','')+':'+" "('1' if os.environ.get('PATH') else '0'))"], env={"PROBE_X": "42"}) self.assertEqual(out.returncode, 0) self.assertEqual(out.stdout, "42:1") def test_call_runner_passes_env_to_default_runner(self): seen = [] def recording(cmd, timeout=None, env=None): seen.append(env) return SimpleNamespace(returncode=0, stdout="", stderr="") ex = DockerExecutor("/fake/host.py", runner=recording, env={"XCM_API_KEY": "placeholder-not-a-real-key"}) ex._call_runner(["docker", "version"], env={"SUB2API_API_KEY": "x"}) self.assertEqual(seen, [{"SUB2API_API_KEY": "x"}])