feat: goal 断点续跑端点(G10)+ 摘要持久化与推送 outbox(G11/G12)

G10:POST /tasks/{id}/goal-resume,仅 interrupted 的 goal 任务,
走 host.py goal-resume(无 --goal-text)从 goal_rounds_done 下一轮
断点续跑,保留原线程与 worktree,状态回 queued 并置
goal_resume_pending(worker 认领后清掉),写 task_goal_resumed
审计;goal-met/unmet、failed、非 goal 一律 409;/continue 开新
循环语义不动。Local/Docker 两路新增 goal_resume_breakpoint_task,
不支持断点的执行器明确失败,绝不回落成 goal 或开新循环。
G11:digest 非失败事件持久化进 push_digest_events,worker 循环
每小时按(项目、订阅)分组汇总发一条,失败类仍即时发。
G12:webhook/slack 投递失败写 push_outbox,worker 循环后台重试
(最多 3 次、默认 60 秒退避),3 次仍失败删行并记日志,不丢
任务状态;缺凭证与无 sender 不进 outbox;文档写明 at-least-once
下 webhook/slack 可能重复,接收方须去重。
测试:cloud 769(4 跳过)、host 68、deploy 19 全过。
This commit is contained in:
host committed 2026-10-28 11:09:29 +08:00
1 parent ac553509ea
commit 5883169c82
8 files changed
+958 -21

No files matched your search

+194
View File
@@ -0,0 +1,194 @@
"""G10 云端 goal 断点续跑单测:端点口径 + worker 断点路由。
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,只断言命令形状与最终状态。
本文件不含任何真实密钥、token、证书或私钥。
"""
import http.client
import json
import os
import sqlite3
import sys
import tempfile
import threading
import unittest
from pathlib import Path
from types import SimpleNamespace
try:
from cloud.auth import AuthStore
from cloud.server import create_server
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.server import create_server
from cloud.worker import Worker
def _goal_met_runner(cmd):
return SimpleNamespace(
returncode=0,
stdout="round 1: turn=completed verify_rc=- verify_out=\n"
"goal met after rounds\n",
stderr="")
class GoalResumeTestCase(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.other_id, self.other_key = self.auth.create_user("other")
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()
status, self.project = self._req(
"POST", "/projects", {"name": "demo"}, self.owner_key)
self.assertEqual(status, 201, self.project)
self.env = {"XCM_API_KEY": "test-placeholder"}
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 key:
hdrs["X-API-Key"] = key
if body is not None:
payload = json.dumps(body)
hdrs["Content-Type"] = "application/json"
conn.request(method, path, body=payload, headers=hdrs)
resp = conn.getresponse()
raw = resp.read()
conn.close()
try:
return resp.status, json.loads(raw.decode("utf-8"))
except ValueError:
return resp.status, raw.decode("utf-8", errors="replace")
def _create(self, **extra):
body = {"project_id": self.project["id"], "prompt": "build it"}
body.update(extra)
return self._req("POST", "/tasks", body, self.owner_key)
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()
def _row(self, task_id):
conn = sqlite3.connect(self.db_path)
try:
row = conn.execute(
"SELECT status, goal_resume_pending FROM tasks"
" WHERE id = ?", (task_id,)).fetchone()
return row
finally:
conn.close()
def test_interrupted_goal_task_resumes_to_queued_with_flag(self):
status, task = self._create(goal_mode=1)
self.assertEqual(status, 201, task)
self._set_status(task["id"], "interrupted")
status, body = self._req(
"POST", "/tasks/%s/goal-resume" % task["id"],
{}, self.owner_key)
self.assertEqual(status, 200, body)
self.assertEqual(body["status"], "queued")
self.assertEqual(body["goal_resume_pending"], 1)
row = self._row(task["id"])
self.assertEqual(row[0], "queued")
self.assertEqual(row[1], 1)
conn = sqlite3.connect(self.db_path)
try:
audit = conn.execute(
"SELECT action FROM audit_log WHERE project_id = ?"
" AND action = 'task_goal_resumed'",
(self.project["id"],)).fetchall()
finally:
conn.close()
self.assertEqual(len(audit), 1)
def test_terminal_and_failed_and_non_goal_all_409(self):
status, goal_task = self._create(goal_mode=1)
self.assertEqual(status, 201, goal_task)
status, plain_task = self._create()
self.assertEqual(status, 201, plain_task)
for task_id, status_value in (
(goal_task["id"], "completed"),
(goal_task["id"], "failed"),
(plain_task["id"], "interrupted")):
self._set_status(task_id, status_value)
status, body = self._req(
"POST", "/tasks/%s/goal-resume" % task_id,
{}, self.owner_key)
self.assertEqual(status, 409, (task_id, status_value, body))
row = self._row(task_id)
self.assertEqual(row[0], status_value)
self.assertEqual(row[1], 0)
def test_non_maintainer_forbidden(self):
status, task = self._create(goal_mode=1)
self.assertEqual(status, 201, task)
self._set_status(task["id"], "interrupted")
status, body = self._req(
"POST", "/tasks/%s/goal-resume" % task["id"],
{}, self.other_key)
self.assertEqual(status, 403, body)
row = self._row(task["id"])
self.assertEqual(row[0], "interrupted")
def test_worker_breakpoint_uses_goal_resume_without_goal_text(self):
# 端点置标记后,worker 认领应走 goal-resume(无 --goal-text),
# 而不是 goal(撞已存在)或 goal-resume --goal-text(开新循环)。
# main(#86)起未指定 executor 的任务默认成 docker,本地
# worker 按认领过滤跳过它是正确行为;本测试要的是本地断点
# 路由,所以显式指定 executor="local"。
status, task = self._create(goal_mode=1, executor="local")
self.assertEqual(status, 201, task)
self._set_status(task["id"], "interrupted")
status, body = self._req(
"POST", "/tasks/%s/goal-resume" % task["id"],
{}, self.owner_key)
self.assertEqual(status, 200, body)
seen = []
def fake(cmd):
seen.append(list(cmd))
return _goal_met_runner(cmd)
worker = Worker(self.db_path, "/fake/host.py", runner=fake,
env=self.env)
result = worker.run_one()
self.assertEqual(result["status"], "completed", result)
self.assertEqual(len(seen), 1)
cmd = seen[0]
self.assertIn("goal-resume", cmd)
self.assertNotIn("--goal-text", cmd)
self.assertNotIn("--max-rounds", cmd)
row = self._row(task["id"])
self.assertEqual(row[0], "completed")
self.assertEqual(row[1], 0)
if __name__ == "__main__":
unittest.main()
+115
View File
@@ -24,7 +24,11 @@ try:
create_subscription,
delete_subscription,
dispatch_event,
list_outbox,
list_pending_digest,
list_subscriptions,
process_outbox_due,
send_digest_due,
send_webhook,
)
except ImportError: # discover -s cloud/tests 时把项目根目录补进 sys.path
@@ -37,7 +41,11 @@ except ImportError: # discover -s cloud/tests 时把项目根目录补进 sys.p
create_subscription,
delete_subscription,
dispatch_event,
list_outbox,
list_pending_digest,
list_subscriptions,
process_outbox_due,
send_digest_due,
send_webhook,
)
@@ -454,5 +462,112 @@ class TestRealSenders(PushTestCase):
self.assertEqual(_RecordingHandler.requests, [])
class TestDigestPersistence(PushTestCase):
"""G11:digest 非失败事件必须持久化、按组汇总发一次。"""
def test_digest_events_persisted_and_sent_once_per_group(self):
self._sub(preference="digest")
calls, sender = self._calls()
result = dispatch_event(
self.conn, "completed", "proj-a", {"task_id": "t-1"},
sender=sender)
self.assertEqual(calls, [])
self.assertEqual(len(result["skipped_for_digest"]), 1)
dispatch_event(
self.conn, "completed", "proj-a", {"task_id": "t-2"},
sender=sender)
pending = list_pending_digest(self.conn, "proj-a")
self.assertEqual(len(pending), 2)
digest = send_digest_due(self.conn, sender=sender)
self.assertEqual(len(digest["sent"]), 1)
self.assertEqual(digest["sent"][0]["count"], 2)
self.assertEqual(len(calls), 1)
message = calls[0]
self.assertEqual(message["event_type"], "digest")
self.assertTrue(message["payload"]["digest"])
self.assertEqual(message["payload"]["count"], 2)
self.assertEqual(list_pending_digest(self.conn, "proj-a"), [])
# 第二次无待发事件,不再重复发。
again = send_digest_due(self.conn, sender=sender)
self.assertEqual(again["sent"], [])
self.assertEqual(len(calls), 1)
def test_failure_events_skip_digest_and_send_immediately(self):
self._sub(preference="digest")
calls, sender = self._calls()
result = dispatch_event(
self.conn, "failed", "proj-a", {"task_id": "t-1"},
sender=sender)
self.assertEqual(len(calls), 1)
self.assertEqual(result["skipped_for_digest"], [])
self.assertEqual(list_pending_digest(self.conn, "proj-a"), [])
class TestOutboxRetry(PushTestCase):
"""G12:推送失败进 outbox、到期重试、3 次后丢弃。"""
def _failing(self):
def sender(message):
raise RuntimeError("downstream down")
return sender
def test_failed_send_enqueued_then_retried_successfully(self):
self._sub(preference="instant")
result = dispatch_event(
self.conn, "failed", "proj-a", {"task_id": "t-1"},
sender=self._failing())
self.assertEqual(len(result["errors"]), 1)
self.assertEqual(len(result["outbox"]), 1)
rows = list_outbox(self.conn, "proj-a")
self.assertEqual(len(rows), 1)
self.assertEqual(rows[0]["attempts"], 0)
# 未到期不重试。
early = process_outbox_due(self.conn, sender=self._failing(),
now=rows[0]["next_attempt_at"] - 1)
self.assertEqual(early["sent"], [])
self.assertEqual(len(list_outbox(self.conn, "proj-a")), 1)
# 到期后成功发送,行删掉。
calls, sender = self._calls()
done = process_outbox_due(
self.conn, sender=sender,
now=rows[0]["next_attempt_at"] + 1)
self.assertEqual(len(done["sent"]), 1)
self.assertEqual(len(calls), 1)
self.assertEqual(calls[0]["event_type"], "failed")
self.assertEqual(list_outbox(self.conn, "proj-a"), [])
def test_three_failures_drop_the_row(self):
self._sub(preference="instant")
dispatch_event(
self.conn, "failed", "proj-a", {"task_id": "t-1"},
sender=self._failing())
self.assertEqual(len(list_outbox(self.conn, "proj-a")), 1)
# now 取远未来 + backoff=0,让三次重试都在同一 now 发生
# (单测确定性;真实退避由上一例的 next_attempt_at 覆盖)。
for i in range(2):
out = process_outbox_due(
self.conn, sender=self._failing(), now=10 ** 10,
backoff_seconds=0)
self.assertEqual(out["failed"], [])
self.assertEqual(len(list_outbox(self.conn, "proj-a")), 1)
out = process_outbox_due(
self.conn, sender=self._failing(), now=10 ** 10,
backoff_seconds=0)
self.assertEqual(len(out["failed"]), 1)
self.assertEqual(out["failed"][0]["attempts"], 3)
self.assertEqual(list_outbox(self.conn, "proj-a"), [])
def test_missing_credential_does_not_enter_outbox(self):
create_subscription(
self.conn, "proj-a", "user-1", "webpush",
"https://example.invalid/endpoint", "instant")
result = dispatch_event(
self.conn, "failed", "proj-a", {"task_id": "t-1"},
sender=self._calls()[1])
self.assertEqual(len(result["errors"]), 1)
self.assertEqual(result["outbox"], [])
self.assertEqual(list_outbox(self.conn, "proj-a"), [])
if __name__ == "__main__":
unittest.main()