Files
codex-app-server/tests/test_client.py
T
host f39ed3654e ci3: lint/mypy 第二阶段清理 + 覆盖率 76% -> 78%(门槛不动)
基底:#251 头 174b631(堆叠于 #242 feat-ci-expand 之上),
基线 origin/main aebc6238;本轨不改 #251 已定语义、不动
workflow 门槛、不删检查、不加 skip。

lint(ruff E,F@120):109 -> 10
- F401 43 -> 0:删未用导入;try/except 双绑定的名字出现
  “打地鼠”(删 except 分支后 try 分支又被标出),两分支
  均已核对正文无引用后清掉;MCP 三模块的 Error 名不删,
  改走 importlib 属性绑定(见下),两路径绑定都保留。
- E702 40 -> 0:全在 host.py main() 的 argparse 段,纯分行,
  tokenize 按分号 token 拆(含 2377 行多行语句只断首个分号);
  一次 5 空格缩进失误已回滚重做并以 ast + 全量 host 测试验证。
- E501 13 -> 0:host.py 5 项随 E702 分行连带清掉;mcp_server
  3 项把描述拆成相邻字面量(AST 比对 24 条工具描述与原值
  完全一致,注意 ruff 按东亚宽度计长,CJK 算 2);test_host
  5 项断开 git commit 参数表。
- E402 8 -> 10:生产侧 2 项清掉(db.py _re、github_app
  _base64 移到顶部,之前无引用、无重名);剩余 10 项全是
  tests/ 的 sys.path 前置 import(6 项旧 + 4 个新测试文件
  沿用同一既定模式),移上去会破坏单文件直跑,有意保留。
- F841 4 -> 0:只去绑定、不删调用(run_task、DB 入队、
  tarfile 上下文、git 提交),各有注释与原测试/新测试覆盖;
  host dispatch_from_branch 新增真实 git 仓库回归测试。
- F811 1 -> 0:server 本地 _row_get 与 peer_messages.row_get
  逐行相同,删本地定义,全部调用点解析到同一 import;
  新增 test_server_row_get(同一对象 + 三路行为)。

mypy(生产范围):24 -> 0,零新增 type: ignore
- no-redef 9 -> 0:MCP 三模块 try/except 两次 from-import
  改 importlib.import_module + 属性绑定(cloud 优先、flat
  copy 回落、内层 ImportError 同样回落,语义与原来一致;
  flat-copy 子进程测试证实回落后 __module__ 为顶层名);
  server _row_get 随 F811 消除。
- arg-type 10 -> 0:harness2_tasks shared 改 TypedDict
  逐键精确类型;CodexProbeAdapter 补 no-op validate_tree
  (_adapter_validate 本就跳过缺失方法,行为一致)。
- var-annotated 3 -> 0:sub2api _SHARED_ADMIN/_login_slots、
  verify-multiuser RESULTS 加精确注解。
- assignment/misc 2 -> 0:marker_tools ZoneInfo 先声明
  Any 再 try import(草稿先验 mypy 通过)。

bandit:总数 286 不变,High 仍 4 项,全在 host.py,本轨不改
(属第 3 项白名单轨范围),只做 triage:
- 1319 run_verify:无插值,整串验测命令,管道/&& 须 shell
  语义(新增 test_host_run_verify 断言管道与 && 真实生效)。
- 1497 notify:模板来自算子配置,三处插值全部 shlex.quote,
  证据为既有 test_notify_failure_quotes_shell_metacharacters
  (; touch 与 $(touch ) 不执行)。
- 2099/2103 goal verify:无插值,任务配置验测串,同 run_verify。
- 无新增 High;pip-audit 0 漏洞。

覆盖率(同口径三套件 coverage 计量):75.96% -> 77.87%
(22392 行/缺 5385 -> 22437 行/缺 4963,显示 76% -> 78%)
- client.py 0% -> 90%(pipe 假子进程 + main 分支)
- run_parallel.py 0% -> 97%、migrate 包装 0% -> 95%
- playwright_mcp 37% -> 62%、imagegen_mcp 47% -> 79%、
  websearch_mcp 51% -> 86%、deploy.py 56% -> 77%
- verify-multiuser 0% -> 27%(仅 check/req helper;main()
  是主机侧真实多用户实弹验证,按门禁不建生产任务、
  不以 mock 冒充,仍为缺口)
- host.py 55% -> 57%(文件 2020 -> 2060 行系 E702 分行
  的计量口径变化,非代码膨胀)
- 未到 85%:门槛保持 75% 不动,不删低覆盖模块出统计口径;
  缺口主力仍是 server.py / worker.py / host.py 大文件,
  下一阶段须针对性深测,非本轨快赢可及。

验证:三套件 1576 -> 1629 项全过(tests 127、cloud/tests
1449 skipped=4、deploy/tests 53);ruff E9 通过;mypy 0;
bandit High 4(同上);pip-audit 0 漏洞;试跑产物已删,
提交后工作树干净。
2026-11-03 02:48:54 +00:00

294 lines
11 KiB
Python

"""client.py 单测(CI 第二阶段覆盖率:基线 0%)。
不跑真实 codex 二进制:AppServer 只跟子进程的 stdin/stdout
说话,本文件用真实 os.pipe 作 stdout 通道(select + os.read
原样走)、BytesIO 作 stdin——JSON-RPC 成帧、审批自动回包、
wait_for 事件分发、initialize/close 都是被测代码的真实逻辑,
只把“子进程是 codex”换成管道。main() 的分支用一个记录型
FakeAppServer 测(断言它发出的请求参数与分支选择)。
"""
import io
import json
import os
import sys
import tempfile
import types
import unittest
from contextlib import redirect_stdout, redirect_stderr
from pathlib import Path
from unittest import mock
REPO_ROOT = Path(__file__).resolve().parents[1]
sys.path.insert(0, str(REPO_ROOT))
import client as client_mod
class FakeProc:
"""Popen 替身:stdout 是真实 pipe(可 select/os.read),
stdin 是 BytesIO(可断言发出的每一行)。"""
def __init__(self, chunks, wait_exc=None):
self.r, self.w = os.pipe()
for chunk in chunks:
os.write(self.w, chunk)
os.close(self.w)
self.stdin = io.BytesIO()
self.stdout = types.SimpleNamespace(fileno=lambda: self.r)
self._wait_exc = wait_exc
self.waited = False
self.killed = False
def poll(self):
return None
def wait(self, timeout=None):
self.waited = True
if self._wait_exc is not None:
raise self._wait_exc
return 0
def kill(self):
self.killed = True
def close_fds(self):
try:
os.close(self.r)
except OSError:
pass
def _line(obj):
return (json.dumps(obj) + "\n").encode()
class AppServerPipeTest(unittest.TestCase):
def _server(self, chunks, codex_home=None, wait_exc=None):
proc = FakeProc(chunks, wait_exc=wait_exc)
self.addCleanup(proc.close_fds)
with mock.patch.object(client_mod.subprocess, "Popen",
return_value=proc):
srv = client_mod.AppServer(codex_home=codex_home)
srv._proc = proc
return srv, proc
def test_request_and_notify_framing(self):
srv, proc = self._server([])
rid = srv.request("thread/list", {"a": 1})
self.assertEqual(rid, 1)
srv.notify("initialized", {})
self.assertEqual(srv.next_id, 2)
lines = proc.stdin.getvalue().decode().splitlines()
self.assertEqual(json.loads(lines[0]),
{"jsonrpc": "2.0", "id": 1, "method": "thread/list",
"params": {"a": 1}})
self.assertEqual(json.loads(lines[1]),
{"jsonrpc": "2.0", "method": "initialized",
"params": {}})
def test_read_msg_answers_approval_then_returns_response(self):
chunks = [_line({"jsonrpc": "2.0", "id": 9,
"method": "approval/request",
"params": {"x": 1}}),
_line({"jsonrpc": "2.0", "id": 1, "result": {"ok": True}})]
srv, proc = self._server(chunks)
srv.approval_policy = "deny"
msg = srv._read_msg(5)
self.assertEqual(msg, {"jsonrpc": "2.0", "id": 1,
"result": {"ok": True}})
sent = proc.stdin.getvalue().decode().splitlines()
self.assertEqual(json.loads(sent[0]),
{"jsonrpc": "2.0", "id": 9,
"result": {"decision": "deny"}})
def test_read_msg_approval_auto(self):
chunks = [_line({"jsonrpc": "2.0", "id": 7,
"method": "permission/request", "params": {}}),
_line({"jsonrpc": "2.0", "id": 1, "result": {}})]
srv, proc = self._server(chunks)
srv.approval_policy = "auto"
with redirect_stderr(io.StringIO()):
msg = srv._read_msg(5)
self.assertEqual(msg["id"], 1)
sent = proc.stdin.getvalue().decode().splitlines()
self.assertEqual(json.loads(sent[0])["result"],
{"decision": "approve"})
def test_wait_for_dispatches_events(self):
chunks = [_line({"jsonrpc": "2.0", "method": "agent/message/delta",
"params": {"item": {"type": "agentMessage",
"text": "hi"}}}),
_line({"jsonrpc": "2.0", "id": 3, "result": {"done": 1}})]
srv, _ = self._server(chunks)
seen = []
msg = srv.wait_for(3, timeout=5, on_event=seen.append)
self.assertEqual(msg["result"], {"done": 1})
self.assertEqual(len(seen), 1)
self.assertEqual(seen[0]["method"], "agent/message/delta")
def test_wait_for_eof_returns_none(self):
srv, _ = self._server([])
self.assertIsNone(srv.wait_for(1, timeout=5))
def test_initialize_success_and_error(self):
chunks = [_line({"jsonrpc": "2.0", "id": 1,
"result": {"codexHome": "/tmp/ch",
"platformOs": "linux"}})]
srv, proc = self._server(chunks)
info = srv.initialize()
self.assertEqual(info["platformOs"], "linux")
sent = proc.stdin.getvalue().decode().splitlines()
self.assertEqual(json.loads(sent[0])["method"], "initialize")
self.assertEqual(json.loads(sent[1])["method"], "initialized")
srv2, _ = self._server(
[_line({"jsonrpc": "2.0", "id": 1,
"error": {"code": -1, "message": "boom"}})])
with self.assertRaises(RuntimeError):
srv2.initialize()
def test_codex_home_created(self):
with tempfile.TemporaryDirectory() as tmp:
home = os.path.join(tmp, "new-home")
srv, proc = self._server([], codex_home=home)
self.assertTrue(os.path.isdir(home))
self.assertEqual(proc.stdin.getvalue(), b"")
def test_close_waits_and_kills_on_timeout(self):
srv, proc = self._server([])
srv.close()
self.assertTrue(proc.waited)
self.assertFalse(proc.killed)
import subprocess as _sp
srv2, proc2 = self._server(
[], wait_exc=_sp.TimeoutExpired("codex", 5))
srv2.close()
self.assertTrue(proc2.killed)
class HandleEventTest(unittest.TestCase):
def test_agent_delta_printed(self):
out = io.StringIO()
with redirect_stdout(out):
client_mod.handle_event(
{"method": "agent/message/delta",
"params": {"item": {"type": "agentMessage",
"text": "hello"}}})
self.assertEqual(out.getvalue(), "hello")
def test_turn_completed_and_error_paths(self):
out, err = io.StringIO(), io.StringIO()
with redirect_stdout(out), redirect_stderr(err):
client_mod.handle_event(
{"method": "turn/completed",
"params": {"status": "completed"}})
# 首分支元组外、含 started 的方法走 stderr 分支。
client_mod.handle_event(
{"method": "session/started", "params": {}})
client_mod.handle_event(
{"method": "something", "params": {"error": "x"}})
self.assertIn("[turn/completed]", out.getvalue())
self.assertIn("[session/started]", err.getvalue())
self.assertIn("[something]", err.getvalue())
class FakeAppServer:
def __init__(self, codex_home=None, extra_args=None):
self.codex_home = codex_home
self.approval_policy = "deny"
self.requests = []
self.notifies = []
self.responses = {}
self.read_msgs = []
self.closed = False
def request(self, method, params=None):
rid = len(self.requests) + 1
self.requests.append((method, params))
return rid
def notify(self, method, params=None):
self.notifies.append((method, params))
def wait_for(self, rid, timeout=60, on_event=None):
return self.responses.get(rid)
def _read_msg(self, timeout):
return self.read_msgs.pop(0) if self.read_msgs else None
def initialize(self):
return {"codexHome": "/tmp/ch", "platformOs": "linux"}
def close(self):
self.closed = True
class ClientMainTest(unittest.TestCase):
def _run(self, argv, setup):
fake = FakeAppServer()
setup(fake)
err = io.StringIO()
with mock.patch.object(client_mod, "AppServer",
return_value=fake), \
mock.patch.object(sys, "argv", argv), \
redirect_stderr(err):
out = io.StringIO()
with redirect_stdout(out):
client_mod.main()
return fake, out.getvalue(), err.getvalue()
def test_list_threads(self):
def setup(fake):
fake.responses[1] = {"result": {"threads": []}}
fake, out, _ = self._run(
["client.py", "--list-threads", "--cwd", "/tmp"],
setup)
self.assertEqual(fake.requests[0][0], "thread/list")
self.assertIn("threads", out)
self.assertTrue(fake.closed)
def test_start_and_turn_completed(self):
def setup(fake):
fake.responses[1] = {"result": {"thread": {"id": "th-9"},
"model": "m"}}
fake.read_msgs.append(
{"method": "turn/completed", "params": {"ok": True}})
fake, out, _ = self._run(
["client.py", "--prompt", "fix it", "--cwd", "/tmp",
"--model", "gpt-x", "--sandbox", "read-only",
"--approval-policy", "never"],
setup)
start = fake.requests[0]
self.assertEqual(start[0], "thread/start")
self.assertEqual(start[1]["approvalPolicy"], "never")
self.assertEqual(start[1]["sandbox"], "read-only")
self.assertEqual(start[1]["model"], "gpt-x")
turn = fake.requests[1]
self.assertEqual(turn[0], "turn/start")
self.assertEqual(turn[1]["threadId"], "th-9")
self.assertEqual(turn[1]["input"][0]["text"], "fix it")
self.assertIn("[done]", out)
self.assertTrue(fake.closed)
def test_resume_failure_prints_and_returns(self):
def setup(fake):
fake.responses[1] = {"error": {"message": "gone"}}
fake, out, err = self._run(
["client.py", "--thread-id", "th-1", "--cwd", "/tmp"],
setup)
self.assertEqual(fake.requests[0][0], "thread/resume")
self.assertIn("thread/resume", err)
self.assertTrue(fake.closed)
def test_no_prompt_prints_thread_id(self):
def setup(fake):
fake.responses[1] = {"result": {"thread": {"id": "th-2"}}}
_, out, _ = self._run(
["client.py", "--cwd", "/tmp"], setup)
self.assertIn("thread_id=th-2", out)
if __name__ == "__main__":
unittest.main()