Files
codex-app-server/cloud/tests/test_task_links.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

486 lines
19 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
"""新业务链路单测:计划模式、后续消息(排队/直接发送)、会话分支。
不跑真实模型回合、不联网:server 侧走本地临时端口 + 临时
SQLite;worker 侧注入假 runner(假 CLI)与假执行器;链路目录
经 server.trace_dir 注入临时目录。
"""
import http.client
import json
import os
import sqlite3
import sys
import tempfile
import threading
import time
import unittest
from pathlib import Path
from types import SimpleNamespace
try:
from cloud.auth import AuthStore
from cloud.sandbox import DockerExecutor
from cloud.server import create_server, 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.auth import AuthStore
from cloud.sandbox import DockerExecutor
from cloud.server import create_server, init_db
from cloud.worker import Worker
def _completed_runner(cmd):
"""假 CLI:dispatch/run 一律成功,打印 host.py 风格的 JSON。"""
if "dispatch" in cmd:
name = cmd[cmd.index("--name") + 1]
elif "run" in cmd:
name = cmd[cmd.index("--task") + 1]
else:
name = "x"
return SimpleNamespace(
returncode=0,
stdout=json.dumps({"task": name, "status": "completed",
"text": "done"}),
stderr="")
class ServerLinksTestCase(unittest.TestCase):
def setUp(self):
self.tmp = tempfile.TemporaryDirectory()
self.db_path = os.path.join(self.tmp.name, "control.db")
self.auth = AuthStore(self.db_path)
self.owner_id, self.owner_key = self.auth.create_user("owner")
self.server = create_server(self.db_path, "127.0.0.1", 0)
self.port = self.server.server_address[1]
self.thread = threading.Thread(
target=self.server.serve_forever, daemon=True)
self.thread.start()
self.trace_dir = os.path.join(self.tmp.name, "host-traces")
os.makedirs(self.trace_dir, exist_ok=True)
self.server.trace_dir = self.trace_dir
status, self.project = self._req(
"POST", "/projects", {"name": "demo"}, self.owner_key)
self.assertEqual(status, 201)
def tearDown(self):
self.server.shutdown()
self.server.server_close()
self.thread.join(timeout=5)
try:
self.auth.conn.close()
except Exception:
pass
self.tmp.cleanup()
def _req(self, method, path, body=None, key=None):
conn = http.client.HTTPConnection(
"127.0.0.1", self.port, timeout=10)
hdrs = {}
payload = None
if body is not None:
payload = json.dumps(body).encode("utf-8")
hdrs["Content-Type"] = "application/json"
if key is not None:
hdrs["X-API-Key"] = key
try:
conn.request(method, path, body=payload, headers=hdrs)
resp = conn.getresponse()
data = resp.read()
finally:
conn.close()
try:
parsed = json.loads(data.decode("utf-8")) if data else None
except ValueError:
parsed = None
return resp.status, parsed
def _create_task(self, **extra):
body = {"project_id": self.project["id"], "prompt": "做一个加法函数"}
body.update(extra)
status, task = self._req("POST", "/tasks", body, self.owner_key)
self.assertEqual(status, 201, task)
return task
def _set_status(self, task_id, status):
conn = sqlite3.connect(self.db_path)
try:
conn.execute("UPDATE tasks SET status = ? WHERE id = ?",
(status, task_id))
conn.commit()
finally:
conn.close()
# -- 计划模式 -------------------------------------------------------
def test_plan_full_conflict_400(self):
status, body = self._req(
"POST", "/tasks",
{"project_id": self.project["id"], "prompt": "p",
"plan": 1, "approval": "full"},
self.owner_key)
self.assertEqual(status, 400)
def test_plan_goal_conflict_400(self):
status, body = self._req(
"POST", "/tasks",
{"project_id": self.project["id"], "prompt": "p",
"plan": 1, "verify_command": "true"},
self.owner_key)
self.assertEqual(status, 400)
def test_plan_create_roundtrip(self):
task = self._create_task(plan=1, approval="ask")
self.assertEqual(task.get("plan"), 1)
status, got = self._req(
"GET", "/tasks/" + task["id"], key=self.owner_key)
self.assertEqual(status, 200)
self.assertEqual(got.get("plan"), 1)
# -- 后续消息 -------------------------------------------------------
def test_followup_validation(self):
status, _ = self._req(
"POST", "/tasks/nope/followups",
{"body": "hi"}, self.owner_key)
self.assertEqual(status, 404)
task = self._create_task()
status, _ = self._req(
"POST", "/tasks/%s/followups" % task["id"],
{"body": " "}, self.owner_key)
self.assertEqual(status, 400)
status, _ = self._req(
"POST", "/tasks/%s/followups" % task["id"],
{"body": "hi", "mode": "bogus"}, self.owner_key)
self.assertEqual(status, 400)
# 终态任务拒绝后续消息。
self._set_status(task["id"], "completed")
status, _ = self._req(
"POST", "/tasks/%s/followups" % task["id"],
{"body": "hi"}, self.owner_key)
self.assertEqual(status, 409)
# goal 任务拒绝后续消息。
goal = self._create_task(verify_command="true")
status, _ = self._req(
"POST", "/tasks/%s/followups" % goal["id"],
{"body": "hi"}, self.owner_key)
self.assertEqual(status, 409)
def test_followup_create_and_list(self):
task = self._create_task()
status, fu1 = self._req(
"POST", "/tasks/%s/followups" % task["id"],
{"body": "先排队"}, self.owner_key)
self.assertEqual(status, 201, fu1)
self.assertEqual(fu1["status"], "pending")
status, fu2 = self._req(
"POST", "/tasks/%s/followups" % task["id"],
{"body": "直接发", "mode": "direct"}, self.owner_key)
self.assertEqual(status, 201, fu2)
status, listing = self._req(
"GET", "/tasks/%s/followups" % task["id"], key=self.owner_key)
self.assertEqual(status, 200)
self.assertEqual([f["body"] for f in listing["followups"]],
["先排队", "直接发"])
def test_followup_direct_appends_trace(self):
task = self._create_task()
status, _ = self._req(
"POST", "/tasks/%s/followups" % task["id"],
{"body": "立刻看到我", "mode": "direct"}, self.owner_key)
self.assertEqual(status, 201)
path = os.path.join(self.trace_dir, task["id"] + ".jsonl")
with open(path, encoding="utf-8") as f:
entries = [json.loads(line) for line in f if line.strip()]
self.assertEqual(len(entries), 1)
self.assertEqual(entries[0]["phase"], "followup-direct")
self.assertIn("立刻看到我", entries[0]["text"])
# -- 会话分支 -------------------------------------------------------
def test_fork_terminal_inherits_fields(self):
src = self._create_task(model="gpt-5.6-sol", effort="high",
approval="ask", plan=1)
self._set_status(src["id"], "completed")
status, forked = self._req(
"POST", "/tasks/%s/fork" % src["id"],
{"message": "换个方向继续"}, self.owner_key)
self.assertEqual(status, 201, forked)
self.assertEqual(forked["forked_from"], src["id"])
self.assertEqual(forked["status"], "queued")
self.assertEqual(forked["prompt"], "换个方向继续")
self.assertEqual(forked["model"], "gpt-5.6-sol")
self.assertEqual(forked["effort"], "high")
self.assertEqual(forked["approval"], "ask")
self.assertEqual(forked["plan"], 1)
self.assertIsNone(forked.get("verify_command"))
def test_fork_validation(self):
task = self._create_task()
# 运行中(queued)不能分支。
status, _ = self._req(
"POST", "/tasks/%s/fork" % task["id"],
{"message": "x"}, self.owner_key)
self.assertEqual(status, 409)
self._set_status(task["id"], "completed")
status, _ = self._req(
"POST", "/tasks/%s/fork" % task["id"],
{"message": " "}, self.owner_key)
self.assertEqual(status, 400)
status, _ = self._req(
"POST", "/tasks/nope/fork",
{"message": "x"}, self.owner_key)
self.assertEqual(status, 404)
def _insert_task(db_path, task_id, prompt="do work", status="queued",
project_id="p1", **extra):
now = time.time()
cols = ["id", "project_id", "prompt", "status", "idempotency_key",
"depends_on", "priority", "created_by", "created_at",
"updated_at", "last_heartbeat"]
vals = [task_id, project_id, prompt, status, None, "[]", 0, "tester",
now, now, None]
for k, v in extra.items():
cols.append(k)
vals.append(v)
conn = sqlite3.connect(db_path)
try:
conn.execute(
"INSERT INTO tasks(%s) VALUES(%s)"
% (", ".join(cols), ", ".join("?" * len(cols))), vals)
conn.commit()
finally:
conn.close()
def _insert_followup(db_path, task_id, body, mode, created_at,
project_id="p1", status="pending"):
# id 是 TEXT 主键(服务端生成 uuid):不传 id 会插成 NULL,
# CAS 认领 WHERE id = NULL 永远匹配不到,排空会静默跳过。
import uuid
conn = sqlite3.connect(db_path)
try:
conn.execute(
"INSERT INTO task_followups(id, task_id, project_id, body,"
" mode, status, created_by, created_at, updated_at)"
" VALUES(?, ?, ?, ?, ?, ?, 'tester', ?, ?)",
(uuid.uuid4().hex, task_id, project_id, body, mode, status,
created_at, created_at))
conn.commit()
finally:
conn.close()
def _row(db_path, table, task_id=None, fu_id=None):
conn = sqlite3.connect(db_path)
try:
if fu_id is not None:
row = conn.execute(
"SELECT * FROM %s WHERE id = ?" % table,
(fu_id,)).fetchone()
else:
row = conn.execute(
"SELECT * FROM %s WHERE id = ?" % table,
(task_id,)).fetchone()
if row is None:
return None
cols = [d[0] for d in conn.execute(
"SELECT * FROM %s LIMIT 0" % table).description]
return dict(zip(cols, row))
finally:
conn.close()
def _followup_statuses(db_path, task_id):
conn = sqlite3.connect(db_path)
try:
rows = conn.execute(
"SELECT body, status FROM task_followups"
" WHERE task_id = ? ORDER BY id", (task_id,)).fetchall()
finally:
conn.close()
return dict(rows)
class WorkerLinksTestCase(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": "test-placeholder"}
self.calls = []
def tearDown(self):
self.tmp.cleanup()
def _worker(self, runner=None, **kwargs):
kwargs.setdefault("env", self.env)
return Worker(self.db_path, "/fake/host.py",
runner=runner or _completed_runner, **kwargs)
def _recording(self, inner):
def fake(cmd):
self.calls.append(list(cmd))
return inner(cmd)
return fake
# -- 任务级模型优先 -------------------------------------------------
def test_task_model_beats_worker_model(self):
_insert_task(self.db_path, "T", model="gpt-5.6-sol")
worker = self._worker(runner=self._recording(_completed_runner),
model="gpt-5.6-terra")
result = worker.run_one()
self.assertEqual(result["status"], "completed")
dispatch = [c for c in self.calls if "dispatch" in c][0]
self.assertEqual(dispatch[dispatch.index("--model") + 1],
"gpt-5.6-sol")
self.assertEqual(_row(self.db_path, "tasks", "T")["actual_model"],
"gpt-5.6-sol")
# -- 计划模式命令 ---------------------------------------------------
def test_plan_local_command_readonly(self):
_insert_task(self.db_path, "T", plan=1)
worker = self._worker(runner=self._recording(_completed_runner))
worker.run_one()
dispatch = [c for c in self.calls if "dispatch" in c][0]
self.assertIn("--sandbox", dispatch)
self.assertEqual(dispatch[dispatch.index("--sandbox") + 1],
"read-only")
def test_plan_local_command_absent_without_plan(self):
_insert_task(self.db_path, "T")
worker = self._worker(runner=self._recording(_completed_runner))
worker.run_one()
dispatch = [c for c in self.calls if "dispatch" in c][0]
self.assertNotIn("--sandbox", dispatch)
def test_plan_docker_inner_command_readonly(self):
ex = DockerExecutor(config_path="/fake/cfg.json")
cmd = ex._inner_host_command(
"dispatch", "--name", "x", "--task", "hi", sandbox="read-only")
self.assertIn("--sandbox", cmd)
self.assertEqual(cmd[cmd.index("--sandbox") + 1], "read-only")
cmd2 = ex._inner_host_command(
"dispatch", "--name", "x", "--task", "hi")
self.assertNotIn("--sandbox", cmd2)
# -- 后续消息排空 ---------------------------------------------------
def test_followup_drain_order_direct_first(self):
_insert_task(self.db_path, "T", prompt="orig")
now = time.time()
_insert_followup(self.db_path, "T", "q1", "queued", now)
_insert_followup(self.db_path, "T", "d1", "direct", now + 1)
_insert_followup(self.db_path, "T", "q2", "queued", now + 2)
def fake(cmd):
if "dispatch" in cmd:
return SimpleNamespace(
returncode=1, stdout="",
stderr="Traceback: task 已存在:T,先换名或 discard 它")
return _completed_runner(cmd)
worker = self._worker(runner=self._recording(fake))
result = worker.run_one()
self.assertEqual(result["status"], "completed")
prompts = []
for c in self.calls:
if "run" in c:
prompts.append(c[c.index("--prompt") + 1])
self.assertEqual(prompts, ["orig", "d1", "q1", "q2"])
self.assertEqual(_followup_statuses(self.db_path, "T"),
{"q1": "done", "d1": "done", "q2": "done"})
def test_followup_failure_stops_drain(self):
_insert_task(self.db_path, "T", prompt="orig")
now = time.time()
_insert_followup(self.db_path, "T", "bad", "queued", now)
_insert_followup(self.db_path, "T", "later", "queued", now + 1)
def fake(cmd):
if "dispatch" in cmd and "bad" in cmd:
return SimpleNamespace(returncode=1, stdout="",
stderr="boom")
return _completed_runner(cmd)
worker = self._worker(runner=self._recording(fake))
result = worker.run_one()
self.assertEqual(result["status"], "failed")
self.assertEqual(_followup_statuses(self.db_path, "T"),
{"bad": "failed", "later": "pending"})
def test_goal_task_does_not_drain(self):
_insert_task(self.db_path, "T", prompt="orig",
verify_command="true")
def fake(cmd):
if "goal" in cmd:
# goal 结论行:host.py goal 两种结局都 exit 0,
# 结论靠这行解析,没有它会被判无结论。
return SimpleNamespace(returncode=0,
stdout="goal met after rounds\n",
stderr="")
return _completed_runner(cmd)
_insert_followup(self.db_path, "T", "later", "queued", time.time())
worker = self._worker(runner=self._recording(fake))
result = worker.run_one()
self.assertEqual(result["status"], "completed")
self.assertEqual(_followup_statuses(self.db_path, "T"),
{"later": "pending"})
# -- 会话分支 -------------------------------------------------------
def test_fork_runs_first_round_once(self):
_insert_task(self.db_path, "T", prompt="branch msg",
forked_from="SRC")
forks = []
def fake(cmd):
if "fork" in cmd:
forks.append(list(cmd))
return SimpleNamespace(returncode=0,
stdout="forked SRC -> T\n",
stderr="")
if "dispatch" in cmd:
return SimpleNamespace(
returncode=1, stdout="",
stderr="Traceback: task 已存在:T,先换名或 discard 它")
return _completed_runner(cmd)
worker = self._worker(runner=self._recording(fake))
result = worker.run_one()
self.assertEqual(result["status"], "completed")
self.assertEqual(len(forks), 1)
fork = forks[0]
self.assertIn("SRC", fork)
self.assertIn("T", fork)
runs = [c for c in self.calls if "run" in c]
self.assertEqual(len(runs), 1)
self.assertEqual(runs[0][runs[0].index("--prompt") + 1],
"branch msg")
def test_fork_failure_not_retried(self):
_insert_task(self.db_path, "T", prompt="branch msg",
forked_from="SRC")
forks = []
def fake(cmd):
if "fork" in cmd:
forks.append(list(cmd))
return SimpleNamespace(returncode=0,
stdout="forked SRC -> T\n",
stderr="")
if "dispatch" in cmd:
return SimpleNamespace(
returncode=1, stdout="",
stderr="Traceback: task 已存在:T,先换名或 discard 它")
return SimpleNamespace(returncode=1, stdout="",
stderr="model boom")
worker = self._worker(runner=self._recording(fake))
result = worker.run_one()
self.assertEqual(result["status"], "failed")
# range(0) 跳过重试循环:fork 只调一次,绝不重复分叉。
self.assertEqual(len(forks), 1)
if __name__ == "__main__":
unittest.main()