kai/writer-work-flow
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(chain): 修评审 CRITICAL+HIGH — 链网关按 session 重建/日志脱敏/resume 原子化+所有权/死导入

Browse Source 
- CRITICAL #1：链 write/review 节点经 gateway_builder 按节点自建 session 现建网关，
  usage_ledger sink 绑活 session，随节点 commit 持久化；run_chain_job 不再转发请求网关
  （其 session 在 BackgroundTask 跑时已关闭，记账行被静默丢弃）。新增 get_chain_gateway_builder
  缝（仿 digest builder），get_chain_gateway 退化为纯 503 凭据预检。守不变量 #1。
- HIGH #2：chain_runner 失败日志不再记 str(exc)（可能含 key/连接串/LLM 输出），改记
  _classify_job_error 脱敏文案 + exc_type（设计 §5）。
- HIGH #3：resume 端点原子抢占 awaiting→running（JobRepo.claim_awaiting_to_running 条件
  UPDATE），抢不到 → 409，防并发 resume 双 Command(resume) 损坏图。
- HIGH #4：resume 校验 job.project_id == project_id（JobView 新增 project_id），不匹配 → 404。
- HIGH #5：resume 返回新 ChainResumeAccepted{job_id,chain_key}，去掉无意义哨兵 start/count=0。
- HIGH #6：删 nodes.py 死导入 extract_conflicts（import + __all__）。
- 测试 #7：e2e 断言链跑后 usage_ledger 有行（#1 回归守卫）+ chapter_reviews 每章一行；
  新增 claim 原子抢占单测 + resume 跨项目 404 / 并发 409 端点测。
This commit is contained in:
Yaojia Wang
2026-06-23 18:04:10 +02:00
parent 061792db1c
commit d1ea83b191
13 changed files with 316 additions and 37 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
apps/api/tests/fakes_projects.py
View File

@@ -414,7 +414,13 @@ class FakeJobRepo:
self.rows: dict[uuid.UUID, JobView] = {}
async def create(self, project_id: uuid.UUID | None, kind: str) -> JobView:
view = JobView(id=uuid.uuid4(), kind=kind, status=STATUS_QUEUED, progress=0)
view = JobView(
id=uuid.uuid4(),
project_id=project_id,
kind=kind,
status=STATUS_QUEUED,
progress=0,
)
self.rows[view.id] = view
return view
@@ -442,6 +448,15 @@ class FakeJobRepo:
self.rows[job_id] = view
return view
async def claim_awaiting_to_running(self, job_id: uuid.UUID) -> JobView | None:
"""原子抢占 awaiting→running（内存替身：仅当现态 awaiting 才抢到，否则 None）。"""
current = self.rows.get(job_id)
if current is None or current.status != STATUS_AWAITING:
return None
view = current.model_copy(update={"status": STATUS_RUNNING})
self.rows[job_id] = view
return view
async def fail(self, job_id: uuid.UUID, error: str) -> JobView:
view = self.rows[job_id].model_copy(update={"status": STATUS_FAILED, "error": error})
self.rows[job_id] = view

75
apps/api/tests/test_chain.py
View File

@@ -151,6 +151,19 @@ async def _memsaver_ctx(saver: MemorySaver) -> AsyncIterator[Any]:
yield saver
def _async_returning(gateway: Any) -> Any:
"""构造「按 session 建网关」的 builder 替身：忽略 session，恒返给定 mock 网关（绝不联网）。
链节点经 `gateway_builder(session)` 现建网关（不变量 #1）；测试里 ledger 不落库（fake
session），故 builder 只需把 mock 网关交回即可。
"""
async def _build(_session: Any) -> Any:
return gateway
return _build
class _FakeContext:
stable_core = "## 世界观硬规则\n灵气可凝丹"
volatile = "## 写作指令\n写第 N 章"
@@ -169,6 +182,7 @@ def _app(project_repo: FakeProjectRepo, job_repo: FakeJobRepo) -> FastAPI:
from ww_api.services.chain_deps import get_checkpointer_factory
from ww_api.services.project_deps import (
get_chain_gateway,
get_chain_gateway_builder,
get_digest_gateway_builder,
get_job_repo,
get_project_repo,
@@ -182,6 +196,9 @@ def _app(project_repo: FakeProjectRepo, job_repo: FakeJobRepo) -> FastAPI:
app.dependency_overrides[get_session] = lambda: _FakeSession()
app.dependency_overrides[get_session_factory] = lambda: _session_factory
app.dependency_overrides[get_chain_gateway] = lambda: _FakeChainGateway(conflicts=[])
app.dependency_overrides[get_chain_gateway_builder] = lambda: _async_returning(
_FakeChainGateway(conflicts=[])
)
saver = MemorySaver()
app.dependency_overrides[get_checkpointer_factory] = lambda: lambda: _memsaver_ctx(saver)
app.dependency_overrides[get_digest_gateway_builder] = lambda: lambda _s: None
@@ -363,6 +380,56 @@ async def test_resume_chain_job_not_found_returns_404(
assert resp.status_code == 404
async def test_resume_chain_wrong_project_returns_404(
_noop_run_chain_job: list[dict[str, Any]],
) -> None:
"""所有权校验（审评 #4）：job 属项目 A，从项目 B 路径 resume → 404（同案，不枚举）。"""
project_repo = FakeProjectRepo()
job_repo = FakeJobRepo()
pid_a = await _seed_project(project_repo)
pid_b = uuid.UUID(
str((await project_repo.create(PROJECT_OWNER, ProjectCreate(title="作品B"))).id)
)
job = await job_repo.create(pid_a, "chain") # job 属 A
await job_repo.set_awaiting(job.id, {"awaiting_chapter": 1})
app = _app(project_repo, job_repo)
async with _client(app) as client:
resp = await client.post(
f"/projects/{pid_b}/chains/runs/{job.id}/resume", # 从 B 续 A 的 job
json={"decisions": []},
)
assert resp.status_code == 404
assert len(_noop_run_chain_job) == 0 # 未调度
async def test_resume_chain_concurrent_claim_returns_409(
_noop_run_chain_job: list[dict[str, Any]],
) -> None:
"""原子抢占（审评 #3）：第一个 resume 已把 awaiting→running，第二个抢不到 → 409。"""
project_repo = FakeProjectRepo()
job_repo = FakeJobRepo()
pid = await _seed_project(project_repo)
job = await job_repo.create(pid, "chain")
await job_repo.set_awaiting(job.id, {"awaiting_chapter": 1})
# 模拟并发：第一个 resume 已抢占 awaiting→running。
claimed = await job_repo.claim_awaiting_to_running(job.id)
assert claimed is not None
app = _app(project_repo, job_repo)
async with _client(app) as client:
resp = await client.post(
f"/projects/{pid}/chains/runs/{job.id}/resume",
json={"decisions": []},
)
# job 现态 running（非 awaiting）→ 守卫先在 status 检查处 409（CONFLICT）。
assert resp.status_code == 409
assert resp.json()["error"]["code"] == "CONFLICT"
assert len(_noop_run_chain_job) == 0
# ---- 服务层 run_chain_job（直接 await，注入全 fake；job 状态由 fake SqlJobRepo 替身记录）----
@@ -440,7 +507,7 @@ async def test_run_chain_job_no_conflict_completes_done(_patched_runner: None) -
chain_key="draft_volume",
start_chapter_no=1,
count=2,
gateway=gateway,
chain_gateway_builder=_async_returning(gateway),
checkpointer_ctx=lambda: _memsaver_ctx(saver),
accept_op=fakes["accept_op"],
chapter_repo_factory=fakes["chapter_repo_factory"],
@@ -476,7 +543,7 @@ async def test_run_chain_job_conflict_sets_awaiting_then_resume_done(
chain_key="draft_volume",
start_chapter_no=1,
count=1,
gateway=gateway,
chain_gateway_builder=_async_returning(gateway),
checkpointer_ctx=lambda: _memsaver_ctx(saver),
accept_op=fakes["accept_op"],
chapter_repo_factory=fakes["chapter_repo_factory"],
@@ -498,7 +565,7 @@ async def test_run_chain_job_conflict_sets_awaiting_then_resume_done(
chain_key="draft_volume",
start_chapter_no=1,
count=1,
gateway=gateway,
chain_gateway_builder=_async_returning(gateway),
checkpointer_ctx=lambda: _memsaver_ctx(saver),
accept_op=fakes["accept_op"],
chapter_repo_factory=fakes["chapter_repo_factory"],
@@ -532,7 +599,7 @@ async def test_run_chain_job_error_marks_failed_safely(_patched_runner: None) ->
chain_key="draft_volume",
start_chapter_no=1,
count=1,
gateway=_BoomGateway(),
chain_gateway_builder=_async_returning(_BoomGateway()),
checkpointer_ctx=lambda: _memsaver_ctx(MemorySaver()),
accept_op=fakes["accept_op"],
chapter_repo_factory=fakes["chapter_repo_factory"],