云端 goal/merge/review 三事件:goal 循环 + PR 事件通知

此前 goal-unmet/merge-failed/review-requested 只有允许列表,
云端没有生产者(概念只在本地 host.py)。本轮给三者接真生产者:
- goal:POST /tasks 接受 goal/verify_command/goal_max_rounds
  (迁移补列,SQLite 与 Postgres 两支);带 verify_command 的
  任务走 host.py goal 循环(Local/Docker 执行器 goal_task,
  turn→验测→喂回重试,缺省 3 轮);达标 completed,未达标
  failed 且只发 goal-unmet、不重复发 failed;goal 模式下 worker
  级重试/fallback 关闭,同任务 /retry 会撞 host 任务名已存在
  (已在文档写明,须新建任务);CloudExecutor 无 goal 概念,
  如实失败不降级
- review-requested:POST /tasks/{id}/pr 建 PR 成功时发
  (payload 含 pr_url/pr_number)
- merge-failed:PR 落盘(push/建 PR)失败 502 时发(payload
  含 step/error),任务保持 merged、可重调 /pr;跳过时不发
测试:host 29、cloud 469 全过。
This commit is contained in:
host committed 2026-10-26 18:11:12 +08:00
1 parent 26e73124fb
commit 5ee9d291dd
8 files changed
+965 -27

No files matched your search

+167 -1
View File
@@ -18,7 +18,8 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(
os.path.abspath(__file__))))
from queue import TaskQueue, budget_exceeded, order_tasks, ready_tasks
from sandbox import CloudExecutor, DockerExecutor, Executor, LocalExecutor
from sandbox import (CloudExecutor, DockerExecutor, Executor,
LocalExecutor, _parse_goal_output)
def _task(task_id, depends_on=None, priority=0, status="queued"):
@@ -219,5 +220,170 @@ class TestExecutors(unittest.TestCase):
self.assertIn("cloud account", str(ctx.exception))
class TestGoalExecutors(unittest.TestCase):
def test_parse_goal_output(self):
met, err = _parse_goal_output(
"round 1: turn=completed verify_rc=0 verify_out=ok\n"
"goal met after rounds\n")
self.assertTrue(met)
self.assertIsNone(err)
met, err = _parse_goal_output(
"round 1: turn=completed verify_rc=1 verify_out=file missing\n"
"round 2: turn=completed verify_rc=1 verify_out=file missing\n"
"goal unmet after rounds\n")
self.assertFalse(met)
self.assertIn("file missing", err)
self.assertIn("2 rounds", err)
met, err = _parse_goal_output("some other output\n")
self.assertIsNone(met)
met, err = _parse_goal_output("")
self.assertIsNone(met)
def test_local_goal_task_met(self):
seen = []
def fake(cmd):
seen.append(cmd)
return SimpleNamespace(
returncode=0,
stdout="round 1: turn=completed verify_rc=0 verify_out=ok\n"
"goal met after rounds\n",
stderr="")
executor = LocalExecutor("/fake/host.py", runner=fake)
result = executor.goal_task(
{"id": "t1", "prompt": "do it", "verify_command": "test -f x",
"goal_max_rounds": 2, "repo": "/r"})
self.assertEqual(result["status"], "completed")
self.assertTrue(result["goal_met"])
self.assertIsNone(result["goal_error"])
self.assertEqual(result["host_status"], "goal-met")
self.assertIn("goal", seen[0])
self.assertIn("--verify", seen[0])
self.assertIn("test -f x", seen[0])
self.assertIn("/r", seen[0])
self.assertEqual(seen[0][seen[0].index("--max-rounds") + 1], "2")
def test_local_goal_task_unmet(self):
def fake(cmd):
return SimpleNamespace(
returncode=0,
stdout="round 1: turn=completed verify_rc=1 "
"verify_out=file missing\n"
"goal unmet after rounds\n",
stderr="")
result = LocalExecutor("/fake/host.py",
runner=fake).goal_task(
{"id": "t1", "prompt": "do it",
"verify_command": "test -f x"})
self.assertEqual(result["status"], "failed")
self.assertFalse(result["goal_met"])
self.assertIn("file missing", result["goal_error"])
self.assertEqual(result["host_status"], "goal-unmet")
def test_local_goal_task_defaults_prompt_and_rounds(self):
seen = []
def fake(cmd):
seen.append(list(cmd))
return SimpleNamespace(
returncode=0, stdout="goal met after rounds\n", stderr="")
LocalExecutor("/fake/host.py", runner=fake).goal_task(
{"id": "t1", "prompt": "do it", "verify_command": "true"})
self.assertIn("do it", seen[0])
self.assertEqual(seen[0][seen[0].index("--max-rounds") + 1], "3")
def test_local_goal_task_no_conclusion_is_failed_not_completed(self):
def fake(cmd):
return SimpleNamespace(returncode=0, stdout="nothing\n",
stderr="")
result = LocalExecutor("/fake/host.py",
runner=fake).goal_task(
{"id": "t1", "prompt": "do it",
"verify_command": "true"})
self.assertEqual(result["status"], "failed")
self.assertIsNone(result["goal_met"])
self.assertIn("无结论", result["goal_error"])
def test_local_goal_task_nonzero_is_failed(self):
def fake(cmd):
return SimpleNamespace(returncode=1, stdout="", stderr="boom")
result = LocalExecutor("/fake/host.py",
runner=fake).goal_task(
{"id": "t1", "prompt": "do it",
"verify_command": "true"})
self.assertEqual(result["status"], "failed")
self.assertIn("boom", result["goal_error"])
def test_local_goal_task_already_exists_names_retry(self):
def fake(cmd):
return SimpleNamespace(
returncode=1, stdout="",
stderr="Traceback\nRuntimeError: 任务已存在")
result = LocalExecutor("/fake/host.py",
runner=fake).goal_task(
{"id": "t1", "prompt": "do it",
"verify_command": "true"})
self.assertEqual(result["status"], "failed")
self.assertIn("请新建任务", result["goal_error"])
def test_local_goal_task_requires_verify(self):
with self.assertRaises(ValueError):
LocalExecutor("/fake/host.py",
runner=lambda cmd: None).goal_task(
{"id": "t1", "prompt": "do it"})
def test_base_goal_task_not_implemented(self):
with self.assertRaises(NotImplementedError):
Executor().goal_task({"id": "t1"})
def test_popen_goal_command(self):
seen = []
class _FakePopen:
def __init__(self, cmd, **kwargs):
seen.append(list(cmd))
with mock.patch("sandbox.subprocess.Popen", _FakePopen):
LocalExecutor("/fake/host.py").popen_task(
{"id": "t1", "prompt": "do it",
"verify_command": "test -f x", "goal_max_rounds": 2},
kind="goal")
self.assertIn("goal", seen[0])
self.assertIn("test -f x", seen[0])
self.assertEqual(seen[0][seen[0].index("--max-rounds") + 1], "2")
def test_docker_goal_task_unmet(self):
seen = []
def fake_runner(cmd, timeout=None):
seen.append(cmd)
return SimpleNamespace(
returncode=0,
stdout="round 1: turn=completed verify_rc=1 "
"verify_out=file missing\n"
"goal unmet after rounds\n",
stderr="")
with mock.patch("sandbox.shutil.which",
return_value="/usr/bin/docker"):
executor = DockerExecutor(
"/fake/host.py", runner=fake_runner,
env={"XCM_API_KEY": "placeholder-not-a-real-key"})
result = executor.goal_task(
{"id": "t1", "prompt": "do it",
"verify_command": "test -f x"})
self.assertEqual(result["executor"], "docker")
self.assertEqual(result["status"], "failed")
self.assertFalse(result["goal_met"])
self.assertIn("goal", seen[0])
self.assertIn("test -f x", seen[0])
if __name__ == "__main__":
unittest.main()
+267
View File
@@ -0,0 +1,267 @@
"""goal 字段与 PR 事件推送的端点级单测。
- POST /tasks 接受 goal/verify_command/goal_max_rounds,非法值 400。
- init_db 迁移后 tasks 表含 goal 三列。
- POST /tasks/{id}/pr 成功时发 review-requested,落盘失败时发
merge-failed(订阅指向本地回环监听,断言真收到)。
git/gh 一律 fake,不跑真实命令、不联网。
"""
import http.client
import http.server
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.push import create_subscription
from cloud.server import create_server, init_db
except ImportError:
sys.path.insert(0, str(Path(__file__).resolve().parents[2]))
from cloud.auth import AuthStore
from cloud.push import create_subscription
from cloud.server import create_server, init_db
def _result(returncode=0, stdout="", stderr=""):
return SimpleNamespace(returncode=returncode, stdout=stdout,
stderr=stderr)
class _Git:
"""假 git:remote/branch/add/commit/push,记录命令。"""
def __init__(self, remote, branch, push_rc=0):
self.calls = []
self.remote = remote
self.branch = branch
self.push_rc = push_rc
def __call__(self, cmd, cwd):
self.calls.append(list(cmd))
if "remote" in cmd:
return _result(0, self.remote + "\n")
if "branch" in cmd:
return _result(0, self.branch + "\n")
if "add" in cmd:
return _result(0, "")
if "commit" in cmd:
return _result(1, "",
"nothing to commit, working tree clean")
if "push" in cmd:
return _result(self.push_rc, "",
"push rejected" if self.push_rc else "")
return _result(0, "")
class _Gh:
"""假 gh:auth 通过、pr create 回链接。"""
def __init__(self, pr_url):
self.calls = []
self.pr_url = pr_url
def __call__(self, cmd, cwd):
self.calls.append(list(cmd))
if cmd[:2] == ["gh", "auth"]:
return _result(0, "", "")
if cmd[:2] == ["gh", "pr"]:
return _result(0, self.pr_url + "\n")
return _result(0, "")
class _Listener:
"""本地回环 webhook 接收器。"""
def __init__(self):
self.requests = []
outer = self
class Handler(http.server.BaseHTTPRequestHandler):
def do_POST(self):
length = int(self.headers.get("Content-Length") or 0)
body = self.rfile.read(length) if length else b""
outer.requests.append(json.loads(body.decode("utf-8")))
self.send_response(200)
self.send_header("Content-Length", "2")
self.end_headers()
self.wfile.write(b"{}")
def log_message(self, *args):
pass
self.server = http.server.ThreadingHTTPServer(
("127.0.0.1", 0), Handler)
self.thread = threading.Thread(
target=self.server.serve_forever, daemon=True)
self.thread.start()
self.url = "http://127.0.0.1:%d/hook" % \
self.server.server_address[1]
def stop(self):
self.server.shutdown()
self.server.server_close()
self.thread.join(timeout=5)
class GoalPrNotifyTestCase(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.worktrees = os.path.join(self.tmp.name, "worktrees")
os.makedirs(self.worktrees, exist_ok=True)
self.server.host_worktrees_dir = self.worktrees
self.listener = _Listener()
def tearDown(self):
self.listener.stop()
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 _project(self, name="p"):
status, project = self._req(
"POST", "/projects", {"name": name, "auto_pr": 1},
self.owner_key)
self.assertEqual(status, 201, project)
return project["id"]
def _merged_task(self, project_id, task_id):
conn = sqlite3.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(?, ?, ?, 'merged',"
" '[]', 0, 'system', 0, 0, NULL)",
(task_id, project_id, "do it"))
conn.commit()
finally:
conn.close()
os.makedirs(os.path.join(self.worktrees, task_id), exist_ok=True)
def test_create_task_goal_fields(self):
pid = self._project()
status, task = self._req(
"POST", "/tasks",
{"project_id": pid, "prompt": "do it",
"goal": "make x", "verify_command": "test -f x",
"goal_max_rounds": 2},
self.owner_key)
self.assertEqual(status, 201, task)
self.assertEqual(task["goal"], "make x")
self.assertEqual(task["verify_command"], "test -f x")
self.assertEqual(task["goal_max_rounds"], 2)
# 不带 goal 字段:普通任务,字段为空。
status, task = self._req(
"POST", "/tasks",
{"project_id": pid, "prompt": "plain"},
self.owner_key)
self.assertEqual(status, 201, task)
self.assertIsNone(task["goal"])
self.assertIsNone(task["verify_command"])
# 非法轮次:0 与非数字都 400,且不建任务。
for bad in (0, -1, "x"):
status, body = self._req(
"POST", "/tasks",
{"project_id": pid, "prompt": "bad",
"verify_command": "true", "goal_max_rounds": bad},
self.owner_key)
self.assertEqual(status, 400, body)
def test_migration_adds_goal_columns(self):
conn = sqlite3.connect(self.db_path)
try:
cols = {row[1] for row in conn.execute(
"PRAGMA table_info(tasks)").fetchall()}
finally:
conn.close()
self.assertIn("goal", cols)
self.assertIn("verify_command", cols)
self.assertIn("goal_max_rounds", cols)
def test_pr_success_notifies_review_requested(self):
pid = self._project()
create_subscription(
self.db_path, pid, self.owner_id, "webhook",
self.listener.url, "instant")
self._merged_task(pid, "t-pr-ok")
self.server.pr_git_runner = _Git(
"https://github.com/octo/repo.git", "host/t-pr-ok")
self.server.pr_gh_runner = _Gh(
"https://github.com/octo/repo/pull/9")
status, body = self._req(
"POST", "/tasks/t-pr-ok/pr", {}, self.owner_key)
self.assertEqual(status, 200, body)
self.assertEqual(len(self.listener.requests), 1)
event = self.listener.requests[0]
self.assertEqual(event["event_type"], "review-requested")
self.assertEqual(event["task_id"], "t-pr-ok")
self.assertIn("pull/9", event["payload"]["pr_url"])
def test_pr_failure_notifies_merge_failed(self):
pid = self._project()
create_subscription(
self.db_path, pid, self.owner_id, "webhook",
self.listener.url, "instant")
self._merged_task(pid, "t-pr-fail")
self.server.pr_git_runner = _Git(
"https://github.com/octo/repo.git", "host/t-pr-fail",
push_rc=1)
self.server.pr_gh_runner = _Gh(
"https://github.com/octo/repo/pull/9")
status, body = self._req(
"POST", "/tasks/t-pr-fail/pr", {}, self.owner_key)
self.assertEqual(status, 502, body)
self.assertEqual(body["step"], "push")
self.assertEqual(len(self.listener.requests), 1)
event = self.listener.requests[0]
self.assertEqual(event["event_type"], "merge-failed")
self.assertEqual(event["task_id"], "t-pr-fail")
self.assertEqual(event["payload"]["step"], "push")
if __name__ == "__main__":
unittest.main()
+151
View File
@@ -223,6 +223,157 @@ class WorkerTestCase(unittest.TestCase):
server.server_close()
thread.join(timeout=5)
# -- goal 模式 -------------------------------------------------------
def _set_goal(self, task_id, verify="test -f x", goal=None,
rounds=None):
conn = sqlite3.connect(self.db_path)
try:
conn.execute(
"UPDATE tasks SET verify_command = ?, goal = ?,"
" goal_max_rounds = ? WHERE id = ?",
(verify, goal, rounds, task_id))
conn.commit()
finally:
conn.close()
def test_goal_met_notifies_completed(self):
"""goal 达标:任务 completed,发 completed(不发 goal-unmet)。"""
import http.server
import threading
requests = []
class Handler(http.server.BaseHTTPRequestHandler):
def do_POST(self):
length = int(self.headers.get("Content-Length") or 0)
body = self.rfile.read(length) if length else b""
requests.append(json.loads(body.decode("utf-8")))
self.send_response(200)
self.send_header("Content-Length", "2")
self.end_headers()
self.wfile.write(b"{}")
def log_message(self, *args):
pass
server = http.server.ThreadingHTTPServer(
("127.0.0.1", 0), Handler)
thread = threading.Thread(
target=server.serve_forever, daemon=True)
thread.start()
try:
from cloud.push import create_subscription
url = "http://127.0.0.1:%d/hook" % server.server_address[1]
create_subscription(
self.db_path, "p1", "user-1", "webhook", url, "instant")
_insert_task(self.db_path, "A")
self._set_goal("A")
calls = []
def goal_runner(cmd):
calls.append(list(cmd))
return SimpleNamespace(
returncode=0,
stdout="round 1: turn=completed verify_rc=0 "
"verify_out=ok\ngoal met after rounds\n",
stderr="")
worker = self._worker(runner=goal_runner)
results = worker.run_all()
self.assertEqual(
[r["status"] for r in results], ["completed"])
self.assertIn("goal", calls[0])
self.assertEqual(len(requests), 1)
self.assertEqual(requests[0]["event_type"], "completed")
finally:
server.shutdown()
server.server_close()
thread.join(timeout=5)
def test_goal_unmet_notifies_only_goal_unmet(self):
"""goal 未达:任务 failed,只发 goal-unmet,不重复发 failed。"""
import http.server
import threading
requests = []
class Handler(http.server.BaseHTTPRequestHandler):
def do_POST(self):
length = int(self.headers.get("Content-Length") or 0)
body = self.rfile.read(length) if length else b""
requests.append(json.loads(body.decode("utf-8")))
self.send_response(200)
self.send_header("Content-Length", "2")
self.end_headers()
self.wfile.write(b"{}")
def log_message(self, *args):
pass
server = http.server.ThreadingHTTPServer(
("127.0.0.1", 0), Handler)
thread = threading.Thread(
target=server.serve_forever, daemon=True)
thread.start()
try:
from cloud.push import create_subscription
url = "http://127.0.0.1:%d/hook" % server.server_address[1]
create_subscription(
self.db_path, "p1", "user-1", "webhook", url, "instant")
_insert_task(self.db_path, "A")
self._set_goal("A")
def unmet_runner(cmd):
return SimpleNamespace(
returncode=0,
stdout="round 1: turn=completed verify_rc=1 "
"verify_out=file missing\n"
"goal unmet after rounds\n",
stderr="")
worker = self._worker(runner=unmet_runner)
results = worker.run_all()
self.assertEqual([r["status"] for r in results], ["failed"])
self.assertEqual(len(requests), 1)
self.assertEqual(requests[0]["event_type"], "goal-unmet")
self.assertIn("file missing",
requests[0]["payload"]["error"])
finally:
server.shutdown()
server.server_close()
thread.join(timeout=5)
def test_goal_mode_runs_once_despite_retries(self):
"""goal 模式只跑一次:循环内部已多轮重试,worker 级重试
不再叠加(同任务重跑会撞 host 任务名已存在)。"""
_insert_task(self.db_path, "A")
self._set_goal("A")
calls = []
def counting(cmd):
calls.append(cmd)
return SimpleNamespace(
returncode=0,
stdout="round 1: turn=completed verify_rc=1 "
"verify_out=nope\ngoal unmet after rounds\n",
stderr="")
worker = self._worker(runner=counting, max_retries=2)
results = worker.run_all()
self.assertEqual(len(calls), 1)
self.assertEqual(results[0]["status"], "failed")
def test_cloud_executor_goal_unsupported(self):
"""cloud 执行器没有 goal 概念:goal 任务如实失败,
不静默降级成普通 dispatch。"""
from cloud.sandbox import CloudExecutor
_insert_task(self.db_path, "A")
self._set_goal("A")
worker = self._worker(executor=CloudExecutor())
results = worker.run_all()
self.assertEqual(results[0]["status"], "failed")
self.assertIn("不支持 goal", results[0]["error"])
# -- 取消 ------------------------------------------------------------
def test_cancel_queued_task_marks_interrupted(self):
_insert_task(self.db_path, "A")