8275a04903
CI / ai-gates (push) Successful in 38s
新增 app/providers/openai/:client 传输(JSON + multipart)、errors 错误映射、 models 厂商 DTO、capabilities 尺寸算术约束、tasks 同步→异步桥、image 图片业务。 装配与配置同步接入,缺 OPENAI_API_KEY 时跳过装配、服务仍可启动。 与火山视频的三处根本差异及其处置: - 接口同步(无任务 ID、无查询端点)→ SyncTaskRegistry 在本服务内部吸收, 对外仍是 ADR-023 §4 的两段式提交/轮询。代价:本服务从此持有状态,进程重启 丢在途任务,且横向扩容前须先解决任务 ID 只在签发进程内有效的问题。 - 产物是 base64 字节而非 URL → 无过期问题,但字节只在内存里。asset_url 放 data URI 仅为满足领域不变式,绝不能原样写进 media.assets.external_url。 - 图生图走 multipart → 先下载参考图再上传;下载失败与超限按参数错误同步拒绝, 不变成注定失败的后台任务。 两处需要记住的判断: - 尺寸上限「3840x2160」文档未说清是逐边还是按像素。逐边理解会禁掉所有高于 2160 的竖图,而 1024x1536 是文档明示的标准竖图,故必然过严。采用最长边 ≤3840 且总像素 ≤3840×2160,已在 capabilities.py 与取证页标为推断。 - 两份文档都没有错误码表,故 errors.py 以 HTTP 状态码为主、type/code 为辅, 顶部标注「未经文档证实」。429 无线索时按限流而非配额耗尽(猜成配额会把可 重试的限流判死);400 无线索时归服务端错误而非内容被拒(错报会让用户去改 一个其实没问题的提示词)。 一处死锁已修并回归钉住:SyncTaskRegistry 原用 add_done_callback 记录完成时刻, 而快速完成的任务在注册时已 done,回调便同步地在持有非可重入锁的线程里执行。 改为首次被观察到时惰性记录。 测试 166 → 271(+105)。四道门禁逐条读退出码,全绿。 产物转存仍阻塞于存储决策(ADR-023 §7),图片模型因此未播种进 V7 目录。
250 lines
8.6 KiB
Python
250 lines
8.6 KiB
Python
"""同步→异步任务注册表的测试。
|
|
|
|
这一层是 gpt-image-2 与 Seedance 的根本差异所在(同步接口没有任务 ID),也是唯一
|
|
让本服务**持有状态**的地方。它写错的表现是丢任务或内存泄漏,两者都要到生产才显形,
|
|
所以逐条钉住。
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import threading
|
|
import time
|
|
|
|
import pytest
|
|
|
|
from app.domain.generation import (
|
|
Failure,
|
|
GenerationResult,
|
|
Retry,
|
|
TaskState,
|
|
UserFacing,
|
|
)
|
|
from app.providers.openai.client import OpenAiError
|
|
from app.providers.openai.tasks import LOCAL_TASK_PREFIX, SyncTaskRegistry
|
|
|
|
|
|
def succeeded(url: str = "data:image/png;base64,AAA") -> GenerationResult:
|
|
return GenerationResult(
|
|
provider_request_id="", state=TaskState.SUCCEEDED, progress=100, asset_url=url
|
|
)
|
|
|
|
|
|
def wait_until_done(registry: SyncTaskRegistry, task_id: str, timeout: float = 3.0):
|
|
deadline = time.monotonic() + timeout
|
|
while time.monotonic() < deadline:
|
|
result = registry.fetch(task_id)
|
|
if result is not None and result.state.is_terminal:
|
|
return result
|
|
time.sleep(0.01)
|
|
raise AssertionError(f"任务 {task_id} 在 {timeout}s 内未结束")
|
|
|
|
|
|
class TestSubmitReturnsImmediately:
|
|
def test_submit_does_not_block_on_the_slow_call(self):
|
|
"""这是整层存在的理由:同步调用必须在后台跑,提交立刻返回。"""
|
|
registry = SyncTaskRegistry(max_workers=2)
|
|
started = threading.Event()
|
|
release = threading.Event()
|
|
|
|
def slow():
|
|
started.set()
|
|
release.wait(timeout=3)
|
|
return succeeded()
|
|
|
|
begin = time.monotonic()
|
|
task_id = registry.submit(slow)
|
|
elapsed = time.monotonic() - begin
|
|
|
|
assert started.wait(timeout=2)
|
|
# 提交本身几乎不耗时,尽管那个调用还在跑。
|
|
assert elapsed < 0.5
|
|
assert registry.fetch(task_id).state is TaskState.RUNNING
|
|
release.set()
|
|
wait_until_done(registry, task_id)
|
|
registry.shutdown()
|
|
|
|
def test_task_id_is_prefixed_so_logs_distinguish_it_from_a_vendor_id(self):
|
|
registry = SyncTaskRegistry()
|
|
task_id = registry.submit(succeeded)
|
|
assert task_id.startswith(LOCAL_TASK_PREFIX)
|
|
registry.shutdown()
|
|
|
|
def test_ids_are_unique(self):
|
|
registry = SyncTaskRegistry()
|
|
ids = {registry.submit(succeeded) for _ in range(20)}
|
|
assert len(ids) == 20
|
|
registry.shutdown()
|
|
|
|
|
|
class TestInFlightAndCompletedStates:
|
|
def test_running_reports_zero_progress(self):
|
|
# 同步接口不提供进度,只能报 0。契约本就不承诺平滑进度(ADR-023 §10)。
|
|
registry = SyncTaskRegistry()
|
|
release = threading.Event()
|
|
task_id = registry.submit(lambda: (release.wait(timeout=3), succeeded())[1])
|
|
|
|
result = registry.fetch(task_id)
|
|
assert result.state is TaskState.RUNNING
|
|
assert result.progress == 0
|
|
release.set()
|
|
registry.shutdown()
|
|
|
|
def test_completed_result_is_returned_with_the_real_task_id(self):
|
|
"""工作函数拿不到自己的任务 ID,故由注册表在 fetch 时填入。"""
|
|
registry = SyncTaskRegistry()
|
|
task_id = registry.submit(succeeded)
|
|
|
|
result = wait_until_done(registry, task_id)
|
|
assert result.state is TaskState.SUCCEEDED
|
|
assert result.provider_request_id == task_id
|
|
assert result.asset_url is not None
|
|
registry.shutdown()
|
|
|
|
def test_result_can_be_fetched_more_than_once(self):
|
|
# Java 侧可能重复轮询同一个已完成任务(比如一次响应丢了)。
|
|
registry = SyncTaskRegistry()
|
|
task_id = registry.submit(succeeded)
|
|
wait_until_done(registry, task_id)
|
|
|
|
assert registry.fetch(task_id).state is TaskState.SUCCEEDED
|
|
assert registry.fetch(task_id).state is TaskState.SUCCEEDED
|
|
registry.shutdown()
|
|
|
|
|
|
class TestUnknownIdIsIndistinguishableOnPurpose:
|
|
def test_never_existed_returns_none(self):
|
|
"""从未存在过与「进程重启后丢失」无法区分——不假装区分。
|
|
|
|
两种情形对调用方的处置相同:停止轮询、任务判失败。
|
|
"""
|
|
assert SyncTaskRegistry().fetch("local-nonexistent") is None
|
|
|
|
|
|
class TestFailurePropagation:
|
|
def test_a_classified_provider_error_keeps_its_classification(self):
|
|
registry = SyncTaskRegistry()
|
|
failure = Failure(
|
|
Retry.QUOTA, UserFacing.QUOTA_EXHAUSTED, "insufficient_quota", "no credit"
|
|
)
|
|
|
|
def failing():
|
|
raise OpenAiError(failure, 429)
|
|
|
|
task_id = registry.submit(failing)
|
|
result = wait_until_done(registry, task_id)
|
|
|
|
assert result.state is TaskState.FAILED
|
|
assert result.failure.retry is Retry.QUOTA
|
|
assert result.failure.provider_code == "insufficient_quota"
|
|
registry.shutdown()
|
|
|
|
def test_an_unclassified_exception_becomes_a_retryable_failure_naming_its_type(
|
|
self,
|
|
):
|
|
"""未分类异常不该让任务卡住,也不该丢掉线索。
|
|
|
|
把异常类型名放进 provider_code——否则排查时只有一句空洞的错误消息。
|
|
"""
|
|
registry = SyncTaskRegistry()
|
|
|
|
def boom():
|
|
raise ZeroDivisionError("unexpected")
|
|
|
|
task_id = registry.submit(boom)
|
|
result = wait_until_done(registry, task_id)
|
|
|
|
assert result.state is TaskState.FAILED
|
|
assert result.failure.retry is Retry.BACKOFF
|
|
assert result.failure.provider_code == "ZeroDivisionError"
|
|
registry.shutdown()
|
|
|
|
|
|
class TestCapacityIsBounded:
|
|
def test_submitting_beyond_the_cap_is_rejected_rather_than_evicting(self):
|
|
"""满了要拒绝新提交,**不能挤掉在途任务**。
|
|
|
|
挤掉一个在途任务会让一个可能正在计费的调用变成无人认领的开销。
|
|
"""
|
|
registry = SyncTaskRegistry(max_workers=1, max_entries=2)
|
|
release = threading.Event()
|
|
|
|
def blocked():
|
|
release.wait(timeout=3)
|
|
return succeeded()
|
|
|
|
registry.submit(blocked)
|
|
registry.submit(blocked)
|
|
|
|
with pytest.raises(RuntimeError, match="上限"):
|
|
registry.submit(blocked)
|
|
|
|
release.set()
|
|
registry.shutdown()
|
|
|
|
def test_concurrency_is_capped_by_max_workers(self):
|
|
"""并发上限同时也是「同时有多少钱在花」的上界。"""
|
|
registry = SyncTaskRegistry(max_workers=2, max_entries=10)
|
|
concurrent = []
|
|
lock = threading.Lock()
|
|
release = threading.Event()
|
|
|
|
def work():
|
|
with lock:
|
|
concurrent.append(1)
|
|
peak = len(concurrent)
|
|
release.wait(timeout=3)
|
|
with lock:
|
|
concurrent.pop()
|
|
return succeeded(f"data:image/png;base64,{peak}")
|
|
|
|
for _ in range(5):
|
|
registry.submit(work)
|
|
time.sleep(0.2)
|
|
|
|
with lock:
|
|
assert len(concurrent) <= 2
|
|
|
|
release.set()
|
|
registry.shutdown()
|
|
|
|
|
|
class TestExpiryOnlyTouchesCompletedEntries:
|
|
def test_completed_entries_expire(self):
|
|
registry = SyncTaskRegistry(completed_ttl_sec=0.05, max_entries=10)
|
|
task_id = registry.submit(succeeded)
|
|
wait_until_done(registry, task_id)
|
|
time.sleep(0.1)
|
|
|
|
# 清理发生在下一次 submit 时(不额外起一个定时线程——本服务的规模用不上)。
|
|
registry.submit(succeeded)
|
|
assert registry.fetch(task_id) is None
|
|
registry.shutdown()
|
|
|
|
def test_in_flight_entries_are_never_expired(self):
|
|
"""在途任务无论多久都不清——它可能正在花钱。"""
|
|
registry = SyncTaskRegistry(completed_ttl_sec=0.01, max_entries=10)
|
|
release = threading.Event()
|
|
task_id = registry.submit(lambda: (release.wait(timeout=3), succeeded())[1])
|
|
time.sleep(0.1)
|
|
|
|
registry.submit(succeeded)
|
|
# 仍在注册表里。
|
|
assert registry.fetch(task_id) is not None
|
|
assert registry.fetch(task_id).state is TaskState.RUNNING
|
|
|
|
release.set()
|
|
registry.shutdown()
|
|
|
|
def test_ttl_starts_at_completion_not_at_creation(self):
|
|
"""否则一个耗时接近 TTL 的任务会在刚完成时就被清掉——结果还没被取走。"""
|
|
registry = SyncTaskRegistry(completed_ttl_sec=5.0, max_entries=10)
|
|
release = threading.Event()
|
|
task_id = registry.submit(lambda: (release.wait(timeout=3), succeeded())[1])
|
|
time.sleep(0.15)
|
|
release.set()
|
|
wait_until_done(registry, task_id)
|
|
|
|
registry.submit(succeeded)
|
|
assert registry.fetch(task_id).state is TaskState.SUCCEEDED
|
|
registry.shutdown()
|