host
f39ed3654e
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。
364 lines
14 KiB
Python
364 lines
14 KiB
Python
"""HA 阶段 1 单测：pr 任务队列 + worktree_host + /pr 跨主机分支。
|
||
|
||
覆盖：pr_jobs 的 enqueue/claim(CAS)/finish 与去重、tasks 的
|
||
worktree_host 迁移（server 与 worker 两支）、认领时写主机名、
|
||
/pr 在 worktree_host 为别机时排队（不直接跑、不重复排）、
|
||
local worker 的 pr 任务循环（CAS 认领 -> 执行 -> 写回终态）、
|
||
autoscaler 给 worker 强制追加 --host-name。
|
||
|
||
git/GitHub 一律 fake 或 monkeypatch，不跑真实命令、不联网。
|
||
"""
|
||
|
||
import http.client
|
||
import json
|
||
import os
|
||
import socket
|
||
import sqlite3
|
||
import sys
|
||
import tempfile
|
||
import threading
|
||
import unittest
|
||
from pathlib import Path
|
||
|
||
try:
|
||
from cloud.auth import AuthStore
|
||
from cloud.autoscaler import Autoscaler
|
||
from cloud.db import connect as _db_connect
|
||
from cloud.pr_exec import (claim_pr_job, enqueue_pr_job,
|
||
ensure_pr_jobs_table, find_open_pr_job,
|
||
finish_pr_job)
|
||
from cloud.server import create_server, migrate_tasks_table
|
||
from cloud.worker import Worker
|
||
except ImportError:
|
||
sys.path.insert(0, str(Path(__file__).resolve().parents[2]))
|
||
from cloud.auth import AuthStore
|
||
from cloud.autoscaler import Autoscaler
|
||
from cloud.db import connect as _db_connect
|
||
from cloud.pr_exec import (claim_pr_job, enqueue_pr_job,
|
||
ensure_pr_jobs_table, find_open_pr_job,
|
||
finish_pr_job)
|
||
from cloud.server import create_server, migrate_tasks_table
|
||
from cloud.worker import Worker
|
||
|
||
|
||
def _old_tasks_table(db_path):
|
||
conn = sqlite3.connect(db_path)
|
||
try:
|
||
conn.execute(
|
||
"CREATE TABLE tasks(id TEXT PRIMARY KEY, project_id TEXT,"
|
||
" prompt TEXT, status TEXT, depends_on TEXT, priority INTEGER,"
|
||
" created_by TEXT, created_at REAL, updated_at REAL,"
|
||
" last_heartbeat REAL)")
|
||
conn.commit()
|
||
finally:
|
||
conn.close()
|
||
|
||
|
||
def _merged_task(db_path, task_id, project_id, host=None):
|
||
conn = sqlite3.connect(db_path)
|
||
try:
|
||
conn.execute(
|
||
"INSERT INTO tasks(id, project_id, prompt, status,"
|
||
" depends_on, priority, created_by, created_at,"
|
||
" updated_at, last_heartbeat) VALUES(?, ?, ?, 'merged',"
|
||
" '[]', 0, 'system', 0, 0, NULL)",
|
||
(task_id, project_id, "do it"))
|
||
if host is not None:
|
||
conn.execute("UPDATE tasks SET worktree_host = ? WHERE id = ?",
|
||
(host, task_id))
|
||
conn.commit()
|
||
finally:
|
||
conn.close()
|
||
|
||
|
||
class PrJobsTableTestCase(unittest.TestCase):
|
||
def setUp(self):
|
||
self.tmp = tempfile.TemporaryDirectory()
|
||
self.db_path = os.path.join(self.tmp.name, "control.db")
|
||
|
||
def tearDown(self):
|
||
self.tmp.cleanup()
|
||
|
||
def test_enqueue_claim_finish_and_cas(self):
|
||
conn = _db_connect(self.db_path)
|
||
try:
|
||
job1 = enqueue_pr_job(conn, "t1", "p1", "host-a")
|
||
# 第二条入队本身是测试前置（claimed2 要拿到 t2）：只去绑定，不删调用。
|
||
enqueue_pr_job(conn, "t2", "p1", "host-a")
|
||
self.assertIsNotNone(find_open_pr_job(conn, "t1"))
|
||
claimed = claim_pr_job(conn, "host-a")
|
||
self.assertEqual(claimed["task_id"], "t1")
|
||
# 第二次认领拿不到同一任务（CAS），只能拿到下一个。
|
||
claimed2 = claim_pr_job(conn, "host-a")
|
||
self.assertEqual(claimed2["task_id"], "t2")
|
||
self.assertIsNone(claim_pr_job(conn, "host-a"))
|
||
# 别的主机认领不到 host-a 的任务。
|
||
self.assertIsNone(claim_pr_job(conn, "host-b"))
|
||
finish_pr_job(conn, job1, "completed",
|
||
"https://github.com/o/a/pull/1", 1)
|
||
self.assertIsNone(find_open_pr_job(conn, "t1"))
|
||
row = conn.execute(
|
||
"SELECT status, pr_url, pr_number FROM pr_jobs"
|
||
" WHERE id = ?", (job1,)).fetchone()
|
||
self.assertEqual(row[0], "completed")
|
||
self.assertEqual(row[1], "https://github.com/o/a/pull/1")
|
||
self.assertEqual(row[2], 1)
|
||
finally:
|
||
conn.close()
|
||
|
||
# -- G13：队列记费用归属人 + 老表补列 --------------------------------
|
||
def test_enqueue_records_created_by(self):
|
||
conn = _db_connect(self.db_path)
|
||
try:
|
||
enqueue_pr_job(conn, "t1", "p1", "host-a",
|
||
created_by="user-9")
|
||
job = find_open_pr_job(conn, "t1")
|
||
self.assertEqual(job["created_by"], "user-9")
|
||
# 不传时为 None（老调用方），worker 回落 system。
|
||
enqueue_pr_job(conn, "t2", "p1", "host-a")
|
||
self.assertIsNone(find_open_pr_job(conn, "t2")["created_by"])
|
||
finally:
|
||
conn.close()
|
||
|
||
def test_old_table_migration_adds_created_by(self):
|
||
conn = sqlite3.connect(self.db_path)
|
||
try:
|
||
conn.execute(
|
||
"CREATE TABLE pr_jobs(id TEXT PRIMARY KEY,"
|
||
" task_id TEXT NOT NULL, project_id TEXT NOT NULL,"
|
||
" host TEXT NOT NULL, status TEXT NOT NULL, pr_url TEXT,"
|
||
" pr_number INTEGER, error TEXT, created_at REAL,"
|
||
" updated_at REAL, started_at REAL, finished_at REAL)")
|
||
conn.commit()
|
||
finally:
|
||
conn.close()
|
||
conn = _db_connect(self.db_path)
|
||
try:
|
||
ensure_pr_jobs_table(conn)
|
||
cols = {row[1] for row in conn.execute(
|
||
"PRAGMA table_info(pr_jobs)").fetchall()}
|
||
self.assertIn("created_by", cols)
|
||
# 补列后照常排队并记归属人。
|
||
enqueue_pr_job(conn, "t1", "p1", "host-a",
|
||
created_by="user-9")
|
||
self.assertEqual(
|
||
find_open_pr_job(conn, "t1")["created_by"], "user-9")
|
||
finally:
|
||
conn.close()
|
||
|
||
|
||
class WorktreeHostMigrationTestCase(unittest.TestCase):
|
||
def setUp(self):
|
||
self.tmp = tempfile.TemporaryDirectory()
|
||
self.db_path = os.path.join(self.tmp.name, "control.db")
|
||
_old_tasks_table(self.db_path)
|
||
|
||
def tearDown(self):
|
||
self.tmp.cleanup()
|
||
|
||
def test_server_migrate_adds_worktree_host(self):
|
||
conn = _db_connect(self.db_path)
|
||
try:
|
||
migrate_tasks_table(conn)
|
||
cols = {row[1] for row in conn.execute(
|
||
"PRAGMA table_info(tasks)").fetchall()}
|
||
self.assertIn("worktree_host", cols)
|
||
# 再跑一次是 no-op。
|
||
migrate_tasks_table(conn)
|
||
finally:
|
||
conn.close()
|
||
|
||
def test_worker_ensure_adds_worktree_host(self):
|
||
worker = Worker(self.db_path, "/nonexistent/host.py",
|
||
env_key="TEST_KEY")
|
||
conn = _db_connect(self.db_path)
|
||
try:
|
||
worker._ensure_result_columns(conn)
|
||
cols = {row[1] for row in conn.execute(
|
||
"PRAGMA table_info(tasks)").fetchall()}
|
||
self.assertIn("worktree_host", cols)
|
||
finally:
|
||
conn.close()
|
||
|
||
def test_claim_writes_host_name(self):
|
||
worker = Worker(self.db_path, "/nonexistent/host.py",
|
||
env_key="TEST_KEY", host_name="worker-host-9")
|
||
conn = _db_connect(self.db_path)
|
||
try:
|
||
conn.execute(
|
||
"INSERT INTO tasks(id, project_id, prompt, status,"
|
||
" depends_on, priority, created_by, created_at,"
|
||
" updated_at, last_heartbeat) VALUES('t1', 'p1', 'x',"
|
||
" 'queued', '[]', 0, 'system', 0, 0, NULL)")
|
||
conn.commit()
|
||
finally:
|
||
conn.close()
|
||
self.assertTrue(worker._claim("t1", executor="local"))
|
||
conn = _db_connect(self.db_path)
|
||
try:
|
||
row = conn.execute(
|
||
"SELECT status, worktree_host FROM tasks WHERE id = 't1'"
|
||
).fetchone()
|
||
self.assertEqual(row[0], "running")
|
||
self.assertEqual(row[1], "worker-host-9")
|
||
finally:
|
||
conn.close()
|
||
|
||
|
||
class PrEndpointRemoteTestCase(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()
|
||
|
||
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 test_remote_host_queues_and_dedupes(self):
|
||
status, project = self._req(
|
||
"POST", "/projects", {"name": "p", "auto_pr": 1},
|
||
self.owner_key)
|
||
self.assertEqual(status, 201, project)
|
||
# 项目成员默认 owner 即 maintainer（create 时建成员行）。
|
||
_merged_task(self.db_path, "t-remote", project["id"],
|
||
host="elsewhere-host-1")
|
||
status, body = self._req(
|
||
"POST", "/tasks/t-remote/pr", {}, self.owner_key)
|
||
self.assertEqual(status, 200, body)
|
||
self.assertTrue(body.get("pr_queued"))
|
||
self.assertEqual(body.get("worktree_host"), "elsewhere-host-1")
|
||
job_id = body.get("pr_job_id")
|
||
self.assertIsNotNone(job_id)
|
||
# 再调一次：去重，返回同一个 job，不重复排队。
|
||
status, body2 = self._req(
|
||
"POST", "/tasks/t-remote/pr", {}, self.owner_key)
|
||
self.assertEqual(status, 200, body2)
|
||
self.assertEqual(body2.get("pr_job_id"), job_id)
|
||
conn = _db_connect(self.db_path)
|
||
try:
|
||
rows = conn.execute(
|
||
"SELECT COUNT(*) FROM pr_jobs WHERE task_id = 't-remote'"
|
||
).fetchone()
|
||
self.assertEqual(rows[0], 1)
|
||
finally:
|
||
conn.close()
|
||
|
||
|
||
class WorkerPrJobsTestCase(unittest.TestCase):
|
||
def setUp(self):
|
||
self.tmp = tempfile.TemporaryDirectory()
|
||
self.db_path = os.path.join(self.tmp.name, "control.db")
|
||
_old_tasks_table(self.db_path)
|
||
|
||
def tearDown(self):
|
||
self.tmp.cleanup()
|
||
|
||
def test_local_worker_runs_pr_job(self):
|
||
import cloud.worker as worker_mod
|
||
calls = []
|
||
|
||
def _fake_execute(db_path, task_id, user_id, **kwargs):
|
||
calls.append((task_id, user_id))
|
||
return {"pr_url": "https://github.com/o/a/pull/9",
|
||
"pr_number": 9, "branch": "host/t1",
|
||
"auth_via": "pat"}
|
||
|
||
worker = Worker(self.db_path, "/nonexistent/host.py",
|
||
env_key="TEST_KEY", host_name="elsewhere-host-1")
|
||
conn = _db_connect(self.db_path)
|
||
try:
|
||
worker._ensure_result_columns(conn)
|
||
conn.execute(
|
||
"INSERT INTO tasks(id, project_id, prompt, status,"
|
||
" depends_on, priority, created_by, created_at,"
|
||
" updated_at, last_heartbeat) VALUES('t1', 'p1', 'x',"
|
||
" 'merged', '[]', 0, 'system', 0, 0, NULL)")
|
||
conn.commit()
|
||
enqueue_pr_job(conn, "t1", "p1", "elsewhere-host-1")
|
||
enqueue_pr_job(conn, "t2", "p1", "other-host")
|
||
finally:
|
||
conn.close()
|
||
orig = worker_mod.execute_task_pr
|
||
worker_mod.execute_task_pr = _fake_execute
|
||
try:
|
||
results = worker._run_pr_jobs()
|
||
finally:
|
||
worker_mod.execute_task_pr = orig
|
||
self.assertEqual(len(results), 1)
|
||
self.assertEqual(results[0]["task_id"], "t1")
|
||
self.assertEqual(results[0]["status"], "completed")
|
||
self.assertEqual(calls, [("t1", "system")])
|
||
conn = _db_connect(self.db_path)
|
||
try:
|
||
row = conn.execute(
|
||
"SELECT status, pr_url FROM pr_jobs WHERE task_id = 't1'"
|
||
).fetchone()
|
||
self.assertEqual(row[0], "completed")
|
||
self.assertEqual(row[1], "https://github.com/o/a/pull/9")
|
||
# 别的主机的任务没被碰。
|
||
row2 = conn.execute(
|
||
"SELECT status FROM pr_jobs WHERE task_id = 't2'"
|
||
).fetchone()
|
||
self.assertEqual(row2[0], "queued")
|
||
finally:
|
||
conn.close()
|
||
|
||
def test_docker_worker_skips_pr_jobs(self):
|
||
from cloud.sandbox import DockerExecutor
|
||
worker = Worker(self.db_path, "/nonexistent/host.py",
|
||
env_key="TEST_KEY",
|
||
executor=DockerExecutor("/fake/host.py"))
|
||
conn = _db_connect(self.db_path)
|
||
try:
|
||
enqueue_pr_job(conn, "t1", "p1", worker.host_name)
|
||
finally:
|
||
conn.close()
|
||
# P1：Docker worker 不再静默返回空，改为显式 needs_local_worker，
|
||
# 行状态持久化为 needs_local_worker、仍可被 local worker 认领。
|
||
jobs = worker._run_pr_jobs()
|
||
self.assertEqual(len(jobs), 1)
|
||
self.assertEqual(jobs[0]["status"], "needs_local_worker")
|
||
self.assertEqual(jobs[0]["task_id"], "t1")
|
||
|
||
def test_autoscaler_forces_host_name(self):
|
||
scaler = Autoscaler(self.db_path, [])
|
||
cmd = scaler._worker_command("w1")
|
||
self.assertIn("--host-name", cmd)
|
||
self.assertEqual(cmd[cmd.index("--host-name") + 1],
|
||
socket.gethostname())
|