feat: G7 分层 fail-open/fail-closed + G8 Docker 轮询掐断 + G9 worker 忽略 host 预算 + G13/G14 归属(第三批)

- G7:认领门 closed 时查配额异常回 quota_check_unavailable、标 interrupted(可重试/续跑);轮询与轮次边界用 open,异常时回 quota_check_failed——新回合边界拒绝,执行中轮询经 _quota_hit 闭包过滤此串、只记 warning 不杀在跑任务,确认超限才掐断;查询函数本身不吞异常冒充不限额。
- G8:Docker 路径加 _docker_call_with_quota_poll(后台线程跑阻塞式 docker 调用,主循环每 quota_poll_interval_seconds 缺省 30 秒查一次,确认超限按容器名真杀容器,结果改写 quota_exceeded 走统一收尾:interrupted、成本照记、续跑消息保留,配额命中后不走 ALREADY_EXISTS 回落);同步路径保持边界检查。
- G9:worker 路径默认忽略 host max_daily_turns(host.py 顶层 --ignore-host-budget 只清该项,Local/Docker 执行器在子命令前追加,worker CLI 缺省开、--no-ignore-host-budget 关);standalone 直接跑 host.py 时预算照常。
- G13/G14:/pr 不再走 system 豁免,建任务前按请求用户查配额(402/503 均不排队不改状态),队列路 pr_jobs.created_by 记请求用户(老表 ALTER 补列),worker 跑 pr 任务时审计操作人用 created_by(老行回落 system)。注意:G14 原案的 system 豁免(服务端与 worker 写死)与 P1 冲突(P1:system 按普通属主走默认额度,不另设无限额系统预算),本次 rebase 未合入该豁免,system 豁免需另行决策。
- 配额口径与 P0/P1 对齐:无配额行按默认额度(非不限额),只有显式 NULL 行才不限额;无价上限只计 source='actual' 行;缺属主(含父任务回查仍无)拒绝新回合。
- README 配额节同步以上口径与 G15 接受现状(best-effort 超支、UTC 月切分、在跑任务只在轮询/轮次边界响应配额改动)。G4 与 G15 不在本批。
This commit is contained in:
host committed 2026-10-28 11:14:10 +08:00
1 parent 5883169c82
commit e31fcc6cba
11 files changed
+786 -176

No files matched your search

+42 -1
View File
@@ -26,7 +26,8 @@ try:
from cloud.autoscaler import Autoscaler
from cloud.db import connect as _db_connect
from cloud.pr_exec import (claim_pr_job, enqueue_pr_job,
find_open_pr_job, finish_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:
@@ -105,6 +106,46 @@ class PrJobsTableTestCase(unittest.TestCase):
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):
+33
View File
@@ -191,6 +191,39 @@ class TaskOptionsTestCase(unittest.TestCase):
"untrusted")
self.assertNotIn("--sandbox", cmd)
# -- G9:worker 路径默认忽略 host 预算 -------------------------------
def test_local_command_ignore_host_budget_flag(self):
seen = []
def fake_runner(cmd):
seen.append(cmd)
return SimpleNamespace(returncode=0, stdout="{}")
ex = LocalExecutor("/fake/host.py", runner=fake_runner,
ignore_host_budget=True)
ex.dispatch_task({"id": "t1", "prompt": "hi"})
cmd = seen[0]
self.assertIn("--ignore-host-budget", cmd)
# 顶层全局参数,必须在子命令之前。
self.assertLess(cmd.index("--ignore-host-budget"),
cmd.index("dispatch"))
ex2 = LocalExecutor("/fake/host.py", runner=fake_runner)
ex2.dispatch_task({"id": "t1", "prompt": "hi"})
self.assertNotIn("--ignore-host-budget", seen[1])
def test_docker_inner_command_ignore_host_budget_flag(self):
ex = DockerExecutor(config_path="/fake/cfg.json",
ignore_host_budget=True)
cmd = ex._inner_host_command("dispatch", "--name", "x",
"--task", "hi")
self.assertIn("--ignore-host-budget", cmd)
self.assertLess(cmd.index("--ignore-host-budget"),
cmd.index("dispatch"))
ex2 = DockerExecutor(config_path="/fake/cfg.json")
cmd2 = ex2._inner_host_command("dispatch", "--name", "x",
"--task", "hi")
self.assertNotIn("--ignore-host-budget", cmd2)
if __name__ == "__main__":
unittest.main()
+94 -2
View File
@@ -17,14 +17,16 @@ import threading
import unittest
from datetime import date, datetime, timedelta, timezone
from pathlib import Path
from types import SimpleNamespace
from unittest import mock
try:
from cloud.auth import AuthStore
from cloud.server import create_server
from cloud.server import CloudControlPlaneHandler, create_server
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.server import create_server
from cloud.server import CloudControlPlaneHandler, create_server
def _req(port, method, path, body=None, key=None):
@@ -355,6 +357,96 @@ class ServerQuotasTestCase(unittest.TestCase):
self.assertEqual(s, 200, q)
self.assertEqual(q["unpriced_actual_tokens"], 150)
# -- G7:准入点 fail-closed ----------------------------------------
def test_create_quota_lookup_failure_503(self):
with mock.patch.object(
CloudControlPlaneHandler, "_quota_status",
side_effect=RuntimeError("db down")):
s, body = self._create_task()
self.assertEqual(s, 503, body)
self.assertEqual(body["error"], "quota_check_unavailable")
# 没建出任务:状态、任务表都不改。
conn = sqlite3.connect(self.db_path)
try:
n = conn.execute(
"SELECT COUNT(*) FROM tasks").fetchone()[0]
finally:
conn.close()
self.assertEqual(n, 0)
# -- G13:system 豁免(server 侧) -----------------------------------
def test_system_quota_exempt_server(self):
conn = sqlite3.connect(self.db_path)
try:
conn.execute(
"INSERT INTO user_quotas(user_id, quota_usd_micros,"
" updated_at) VALUES('system', 0, 0)")
conn.commit()
finally:
conn.close()
handler = object.__new__(CloudControlPlaneHandler)
handler.server = SimpleNamespace(db_path=self.db_path)
self.assertIsNone(handler._check_quota("system"))
self.assertFalse(handler._reject_if_over_quota("system"))
# -- G13/G14:/pr 按请求人过配额门、队列记归属人 ----------------------
def _merged_remote_task(self):
s, task = self._create_task()
self.assertEqual(s, 201, task)
conn = sqlite3.connect(self.db_path)
try:
conn.execute(
"UPDATE tasks SET status = 'merged',"
" worktree_host = 'elsewhere-host-1' WHERE id = ?",
(task["id"],))
conn.commit()
finally:
conn.close()
return task
def test_pr_blocked_at_quota_no_job(self):
task = self._merged_remote_task()
s, _ = self._set_quota(self.owner_id, 0)
self.assertEqual(s, 200)
s, body = _req(self.port, "POST",
"/tasks/%s/pr" % task["id"], {},
self.owner_key)
self.assertEqual(s, 402, body)
self.assertEqual(body["error"], "quota_exceeded")
conn = sqlite3.connect(self.db_path)
try:
has_table = conn.execute(
"SELECT 1 FROM sqlite_master WHERE type='table'"
" AND name='pr_jobs'").fetchone() is not None
rows = conn.execute(
"SELECT COUNT(*) FROM pr_jobs"
" WHERE task_id = ?", (task["id"],)).fetchone()[0] \
if has_table else 0
status = conn.execute(
"SELECT status FROM tasks WHERE id = ?",
(task["id"],)).fetchone()[0]
finally:
conn.close()
self.assertEqual(rows, 0)
self.assertEqual(status, "merged")
def test_pr_queue_records_created_by(self):
task = self._merged_remote_task()
s, body = _req(self.port, "POST",
"/tasks/%s/pr" % task["id"], {},
self.owner_key)
self.assertEqual(s, 200, body)
self.assertTrue(body.get("pr_queued"))
conn = sqlite3.connect(self.db_path)
try:
row = conn.execute(
"SELECT created_by FROM pr_jobs WHERE task_id = ?",
(task["id"],)).fetchone()
finally:
conn.close()
self.assertIsNotNone(row)
self.assertEqual(row[0], self.owner_id)
if __name__ == "__main__":
unittest.main()
+142
View File
@@ -18,18 +18,22 @@ import sqlite3
import subprocess
import sys
import tempfile
import threading
import time
import unittest
from pathlib import Path
from types import SimpleNamespace
from unittest import mock
try:
from cloud.cost import CostStore
from cloud.sandbox import DockerExecutor, LocalExecutor
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.cost import CostStore
from cloud.sandbox import DockerExecutor, LocalExecutor
from cloud.server import init_db
from cloud.worker import Worker
@@ -330,6 +334,144 @@ class WorkerQuotaTestCase(unittest.TestCase):
task, kind="dispatch", quota_check=lambda: True)
self.assertEqual(result["status"], "quota_exceeded")
# -- G7 分层:门侧 fail-closed、轮询侧 fail-open -------------------
def test_claim_gate_quota_lookup_failure_closed(self):
_insert_task(self.db_path, "T1")
worker = self._worker(_usage_runner(
{"input_tokens": 1, "output_tokens": 1, "total_tokens": 2},
self.calls))
with mock.patch.object(
Worker, "_quota_limit_and_used",
side_effect=RuntimeError("db down")):
result = worker.run_one()
self.assertEqual(result["status"], "interrupted")
self.assertIn("quota_check_unavailable", result["error"])
self.assertEqual(_status(self.db_path, "T1"), "interrupted")
# 门侧拦住:runner 一次没调,也不记成本(cost_records
# 是 CostStore 懒建的,没跑过就根本没有这张表)。
self.assertEqual(self.calls, [])
conn = sqlite3.connect(self.db_path)
try:
has_table = conn.execute(
"SELECT 1 FROM sqlite_master WHERE type='table'"
" AND name='cost_records'").fetchone() is not None
rows = _cost_rows(self.db_path, "T1") if has_table else []
finally:
conn.close()
self.assertEqual(rows, [])
def test_poll_quota_lookup_failure_open(self):
_insert_task(self.db_path, "T1")
worker = self._worker(_usage_runner(
{"input_tokens": 1, "output_tokens": 1, "total_tokens": 2},
self.calls))
task = worker.get_task("T1")
with mock.patch.object(
Worker, "_quota_limit_and_used",
side_effect=RuntimeError("db down")):
# 默认 on_error="open":异常不冒充超限,放行。
self.assertIsNone(worker._quota_exceeded(task, None))
self.assertIsNone(worker._quota_exceeded(task, None,
on_error="open"))
# -- G13:system 豁免(worker 侧) ----------------------------------
def test_system_task_exempt_from_quota(self):
_insert_quota(self.db_path, "system", 0)
_insert_task(self.db_path, "T1", created_by="system")
worker = self._worker(_usage_runner(
{"input_tokens": 100, "output_tokens": 10, "total_tokens": 110},
self.calls))
result = worker.run_one()
self.assertEqual(result["status"], "completed")
self.assertEqual(_status(self.db_path, "T1"), "completed")
# -- G8 Docker 轮询掐断 ---------------------------------------------
def test_docker_quota_poll_kills_container(self):
_insert_quota(self.db_path, "tester", QUOTA)
_insert_task(self.db_path, "T1")
_insert_followup(self.db_path, "fu1", "T1")
executor = _BlockingDockerExecutor()
worker = Worker(self.db_path, "/fake/host.py",
env=self.env, model="gpt-6.1-sol",
executor=executor, retry_backoff_seconds=0,
quota_poll_interval_seconds=0.01)
calls = {"n": 0}
def fake_limit(owner):
calls["n"] += 1
# 第 1 次是认领门(未超限,放行);之后轮询一律超限。
# helper 在 rebase 合并 #86 无价上限后返回 4 元组
# (quota, used, month, unpriced_used),此处无价
# 用量为 0,不触发无价上限。
return (QUOTA, 90000 if calls["n"] == 1 else QUOTA,
"2026-10", 0)
worker._quota_limit_and_used = fake_limit
result = worker.run_one()
self.assertEqual(result["status"], "interrupted")
self.assertIn("quota_exceeded", result["error"])
self.assertEqual(_status(self.db_path, "T1"), "interrupted")
self.assertEqual(executor.killed, ["codex-T1"])
# 续跑消息保留(仍 pending),已花成本照记。
self.assertEqual(_followup_status(self.db_path, "fu1"), "pending")
self.assertEqual(len(_cost_rows(self.db_path, "T1")), 1)
# -- G9:Worker 把 ignore 开关同步给外部执行器 ----------------------
def test_worker_syncs_ignore_host_budget_to_executor(self):
worker = Worker(self.db_path, "/fake/host.py",
env=self.env, model="gpt-6.1-sol",
executor=LocalExecutor("/fake/host.py"),
retry_backoff_seconds=0)
self.assertTrue(worker.ignore_host_budget)
self.assertTrue(worker.executor.ignore_host_budget)
worker2 = Worker(self.db_path, "/fake/host.py",
env=self.env, model="gpt-6.1-sol",
executor=LocalExecutor("/fake/host.py"),
ignore_host_budget=False,
retry_backoff_seconds=0)
self.assertFalse(worker2.ignore_host_budget)
self.assertFalse(worker2.executor.ignore_host_budget)
def test_docker_quota_poll_failure_open(self):
_insert_task(self.db_path, "T1")
worker = Worker(self.db_path, "/fake/host.py",
env=self.env, model="gpt-6.1-sol",
quota_poll_interval_seconds=0.01)
task = worker.get_task("T1")
def slow_fn():
time.sleep(0.05)
return {"status": "completed"}
def bad_check():
raise RuntimeError("db down")
result = worker._docker_call_with_quota_poll(
task, slow_fn, bad_check)
self.assertEqual(result["status"], "completed")
class _BlockingDockerExecutor(DockerExecutor):
"""G8 单测用假 Docker:dispatch 阻塞到被 kill,绝不调真 docker。"""
def __init__(self):
super().__init__(host_py_path="/fake/host.py")
self.killed = []
self._stop = threading.Event()
def dispatch_task(self, task, timeout=None, extra_mounts=None,
network=None, extra_env=None, seed_host_dir=None,
model_provider=None):
self._stop.wait(timeout=10)
return {"status": "failed", "stdout": "", "stderr": "killed",
"usage": {"input_tokens": 100, "cached_input_tokens": 0,
"output_tokens": 10, "total_tokens": 110}}
def kill_container(self, name):
self.killed.append(name)
self._stop.set()
return True
if __name__ == "__main__":
unittest.main()