cat-shark
b16e0e9f3c
调度与状态机： - 修复 PAUSED 任务被拾起后复活执行（点击暂停反而开始任务）：next_queued_run 只取 QUEUED，execute_run 以 PAUSED 进入直接返回，暂停必须显式 resume - 重启恢复：启动时 recover_interrupted_runs 把遗留 RUNNING 置 QUEUED（保留产物） - 暂停信号 paused.flag：暂停接口写、继续/重试清除，OCR 逐帧检查秒级中断， 节点内被暂停保持 PAUSED 不误报 FAILED - 调度轮询容错：_loop 异常不杀死线程（曾致任务永久停留 QUEUED） subtitle-ocr 节点级断点： - ocr_partial.jsonl 逐帧存档，重启/暂停后只处理未处理帧，产物与一次跑完一致 - 进度日志携带窗口平均耗时与线程数；取消后抑制进度日志井喷 llm-filter 过滤质量与限流自适应： - 上下文净化：喂给 LLM 的是过滤后的字幕（规则层垃圾从上下文剔除） - 正则确定性过滤：裸网址域名、HTML/水印模式直接删除 - 429/5xx 指数退避重试；worker 限流错误 report_failure 内存临时降最大线程数 并缩容（无错误窗口回升），失败条目降并发后重试一轮 - 保留长文本保护（noise 不删 ≥min_keep_len 文本，LLM 判定不稳的必要兜底） 前端： - 工作流编排页支持选择工作流编辑（加载最新/历史版本）、版本历史面板、 新建/编辑双模式；管理后台编辑跳转 workflow.html?edit=<id> 工作流：ocr-subtitle v7（filter pool_max_workers=20、pool_fast_threshold=1）
321 lines
12 KiB
Python
321 lines
12 KiB
Python
"""用户应用 API 测试。
|
|
|
|
覆盖已发布应用的上传建任务、进度查询、产物下载、失败重试以及
|
|
未发布/无版本工作流的拒绝逻辑。节点为内置注册，无需再手动注册。
|
|
"""
|
|
|
|
from pathlib import Path
|
|
|
|
from fastapi.testclient import TestClient
|
|
|
|
from wov_app.main import app
|
|
|
|
|
|
def _create_published_echo_workflow(client) -> str:
|
|
"""创建一个已发布的单节点 Echo 工作流（echo 为内置节点）。"""
|
|
definition = {
|
|
"name": "echo-flow",
|
|
"version": 1,
|
|
"nodes": [
|
|
{
|
|
"id": "step",
|
|
"node_type": "echo",
|
|
"inputs": {"file_uri": "input.video_uri"},
|
|
}
|
|
],
|
|
"edges": [],
|
|
"entry_inputs": {"video_uri": "file"},
|
|
"final_outputs": {"result": "step.file_uri"},
|
|
}
|
|
client.post(
|
|
"/api/admin/workflows",
|
|
json={
|
|
"id": "echo-app",
|
|
"name": "Echo App",
|
|
"description": "upload a file",
|
|
"definition": definition,
|
|
},
|
|
)
|
|
client.post("/api/admin/workflows/echo-app/publish")
|
|
return "echo-app"
|
|
|
|
|
|
def test_upload_run_progress_and_download() -> None:
|
|
"""验证上传文件建任务、手动执行、查询产物与下载的完整流程。"""
|
|
with TestClient(app) as client:
|
|
workflow_id = _create_published_echo_workflow(client)
|
|
apps = client.get("/api/apps")
|
|
assert apps.status_code == 200
|
|
assert any(item["id"] == workflow_id for item in apps.json())
|
|
|
|
uploaded = client.post(
|
|
f"/api/apps/{workflow_id}/runs",
|
|
files={"file": ("sample.txt", b"hello from upload", "text/plain")},
|
|
)
|
|
assert uploaded.status_code == 200
|
|
run_id = uploaded.json()["id"]
|
|
assert uploaded.json()["status"] == "QUEUED"
|
|
|
|
run = client.get(f"/api/runs/{run_id}")
|
|
assert run.status_code == 200
|
|
assert run.json()["input_uri"].endswith("sample.txt")
|
|
assert run.json()["artifacts"] == []
|
|
|
|
scheduler = app.state.scheduler
|
|
scheduler.execute_run(run_id)
|
|
|
|
completed = client.get(f"/api/runs/{run_id}")
|
|
assert completed.status_code == 200
|
|
assert completed.json()["status"] == "COMPLETED"
|
|
artifact_names = [item["name"] for item in completed.json()["artifacts"]]
|
|
assert "result" in artifact_names
|
|
|
|
artifacts = client.get(f"/api/runs/{run_id}/artifacts")
|
|
assert artifacts.status_code == 200
|
|
assert len(artifacts.json()) >= 1
|
|
|
|
downloaded = client.get(f"/api/runs/{run_id}/artifacts/result")
|
|
assert downloaded.status_code == 200
|
|
assert b"hello from upload" in downloaded.content
|
|
|
|
assert client.get(f"/api/runs/{run_id}/artifacts/missing").status_code == 404
|
|
assert client.get("/api/runs/missing").status_code == 404
|
|
assert client.get("/api/runs/missing/artifacts").status_code == 404
|
|
|
|
db = app.state.db
|
|
db.create_artifact(
|
|
{
|
|
"run_id": run_id,
|
|
"node_id": "step",
|
|
"name": "missing-file",
|
|
"uri": str(Path(__file__).resolve().parent / "not-exists.bin"),
|
|
"mime_type": "text/plain",
|
|
"size": 0,
|
|
}
|
|
)
|
|
assert client.get(f"/api/runs/{run_id}/artifacts/missing-file").status_code == 404
|
|
|
|
runs = client.get("/api/runs")
|
|
assert runs.status_code == 200
|
|
assert any(item["id"] == run_id for item in runs.json())
|
|
|
|
|
|
def test_upload_rejects_unpublished_workflow() -> None:
|
|
"""验证草稿或不存在的工作流不能被用户发起任务。"""
|
|
with TestClient(app) as client:
|
|
client.post(
|
|
"/api/admin/workflows",
|
|
json={
|
|
"id": "draft",
|
|
"name": "Draft",
|
|
"definition": {
|
|
"name": "Draft",
|
|
"version": 1,
|
|
"nodes": [],
|
|
"edges": [],
|
|
},
|
|
},
|
|
)
|
|
response = client.post(
|
|
"/api/apps/draft/runs",
|
|
files={"file": ("x.txt", b"x", "text/plain")},
|
|
)
|
|
assert response.status_code == 404
|
|
|
|
response = client.post(
|
|
"/api/apps/missing/runs",
|
|
files={"file": ("x.txt", b"x", "text/plain")},
|
|
)
|
|
assert response.status_code == 404
|
|
|
|
|
|
def test_upload_rejects_workflow_without_version() -> None:
|
|
"""验证已发布但没有任何版本的工作流返回 422。"""
|
|
with TestClient(app) as client:
|
|
db = app.state.db
|
|
db.upsert_workflow(
|
|
{"id": "empty", "name": "Empty", "published": 1, "latest_version": 0}
|
|
)
|
|
response = client.post(
|
|
"/api/apps/empty/runs",
|
|
files={"file": ("x.txt", b"x", "text/plain")},
|
|
)
|
|
assert response.status_code == 422
|
|
|
|
|
|
def test_retry_failed_run_requeues_and_reruns() -> None:
|
|
"""验证失败任务重试会清空旧产物并重新执行成功。"""
|
|
with TestClient(app) as client:
|
|
workflow_id = _create_published_echo_workflow(client)
|
|
uploaded = client.post(
|
|
f"/api/apps/{workflow_id}/runs",
|
|
files={"file": ("sample.txt", b"hello retry", "text/plain")},
|
|
)
|
|
run_id = uploaded.json()["id"]
|
|
db = app.state.db
|
|
db.update_run(
|
|
run_id,
|
|
status="FAILED",
|
|
error="boom",
|
|
updated_at="2026-01-01T00:00:00+00:00",
|
|
)
|
|
db.create_artifact(
|
|
{
|
|
"run_id": run_id,
|
|
"node_id": "step",
|
|
"name": "stale",
|
|
"uri": "stale.txt",
|
|
"mime_type": "text/plain",
|
|
"size": 1,
|
|
}
|
|
)
|
|
|
|
response = client.post(f"/api/runs/{run_id}/retry")
|
|
|
|
assert response.status_code == 200
|
|
assert response.json() == {"id": run_id, "status": "QUEUED"}
|
|
run = client.get(f"/api/runs/{run_id}").json()
|
|
assert run["status"] == "QUEUED"
|
|
assert run["error"] is None
|
|
assert run["artifacts"] == []
|
|
|
|
app.state.scheduler.execute_run(run_id)
|
|
completed = client.get(f"/api/runs/{run_id}").json()
|
|
assert completed["status"] == "COMPLETED"
|
|
assert any(item["name"] == "result" for item in completed["artifacts"])
|
|
|
|
|
|
def test_pause_resume_run_api() -> None:
|
|
"""验证暂停/继续接口：QUEUED→PAUSED→QUEUED，状态非法时报 422。"""
|
|
with TestClient(app) as client:
|
|
workflow_id = _create_published_echo_workflow(client)
|
|
uploaded = client.post(
|
|
f"/api/apps/{workflow_id}/runs",
|
|
files={"file": ("sample.txt", b"hello pause", "text/plain")},
|
|
)
|
|
run_id = uploaded.json()["id"]
|
|
assert uploaded.json()["status"] == "QUEUED"
|
|
|
|
from wov_app.config import STORAGE_DIR
|
|
flag = STORAGE_DIR / "runs" / run_id / "paused.flag"
|
|
|
|
paused = client.post(f"/api/runs/{run_id}/pause")
|
|
assert paused.status_code == 200
|
|
assert paused.json() == {"id": run_id, "status": "PAUSED"}
|
|
assert client.get(f"/api/runs/{run_id}").json()["status"] == "PAUSED"
|
|
# 暂停时写入暂停信号文件，供运行中的节点（如 OCR）逐帧检查并中止。
|
|
assert flag.exists()
|
|
|
|
resumed = client.post(f"/api/runs/{run_id}/resume")
|
|
assert resumed.status_code == 200
|
|
assert resumed.json() == {"id": run_id, "status": "QUEUED"}
|
|
assert client.get(f"/api/runs/{run_id}").json()["status"] == "QUEUED"
|
|
# 继续时清除暂停信号，避免误触发节点内暂停。
|
|
assert not flag.exists()
|
|
|
|
# 非 PAUSED 任务不可继续。
|
|
assert client.post(f"/api/runs/{run_id}/resume").status_code == 422
|
|
# 不存在的任务 404。
|
|
assert client.post("/api/runs/missing/pause").status_code == 404
|
|
assert client.post("/api/runs/missing/resume").status_code == 404
|
|
|
|
|
|
def test_pause_rejects_terminal_states() -> None:
|
|
"""验证已完成任务不可暂停。"""
|
|
with TestClient(app) as client:
|
|
workflow_id = _create_published_echo_workflow(client)
|
|
uploaded = client.post(
|
|
f"/api/apps/{workflow_id}/runs",
|
|
files={"file": ("sample.txt", b"hello done", "text/plain")},
|
|
)
|
|
run_id = uploaded.json()["id"]
|
|
db = app.state.db
|
|
db.update_run(run_id, status="COMPLETED", progress=1.0, updated_at="2026-01-01T00:00:00+00:00")
|
|
assert client.post(f"/api/runs/{run_id}/pause").status_code == 422
|
|
|
|
|
|
def test_retry_rejects_non_failed_and_missing_runs() -> None:
|
|
"""验证只有 FAILED 状态且存在的任务才能重试。"""
|
|
with TestClient(app) as client:
|
|
workflow_id = _create_published_echo_workflow(client)
|
|
uploaded = client.post(
|
|
f"/api/apps/{workflow_id}/runs",
|
|
files={"file": ("sample.txt", b"x", "text/plain")},
|
|
)
|
|
run_id = uploaded.json()["id"]
|
|
|
|
assert client.post(f"/api/runs/{run_id}/retry").status_code == 422
|
|
assert client.post("/api/runs/missing/retry").status_code == 404
|
|
|
|
|
|
def test_delete_run_removes_record_and_files() -> None:
|
|
"""验证删除任务会清理数据库记录与磁盘上的上传/步骤文件。"""
|
|
import shutil
|
|
|
|
from wov_app.config import STORAGE_DIR
|
|
|
|
with TestClient(app) as client:
|
|
workflow_id = _create_published_echo_workflow(client)
|
|
uploaded = client.post(
|
|
f"/api/apps/{workflow_id}/runs",
|
|
files={"file": ("sample.txt", b"hello delete", "text/plain")},
|
|
)
|
|
run_id = uploaded.json()["id"]
|
|
|
|
# 执行任务以生成步骤产物目录。
|
|
app.state.scheduler.execute_run(run_id)
|
|
run = client.get(f"/api/runs/{run_id}").json()
|
|
steps_dir = STORAGE_DIR / "runs" / run_id
|
|
assert steps_dir.is_dir()
|
|
# 上传文件目录也应存在。
|
|
upload_dir = Path(run["input_uri"]).parent
|
|
assert upload_dir.is_dir()
|
|
|
|
deleted = client.delete(f"/api/runs/{run_id}")
|
|
assert deleted.status_code == 200
|
|
assert deleted.json() == {"deleted": run_id}
|
|
|
|
assert client.get(f"/api/runs/{run_id}").status_code == 404
|
|
assert not steps_dir.exists()
|
|
assert not upload_dir.exists()
|
|
|
|
# 删除不存在的任务返回 404。
|
|
assert client.delete(f"/api/runs/missing").status_code == 404
|
|
|
|
# 清理测试遗留的 runs 目录，避免跨用例残留。
|
|
shutil.rmtree(STORAGE_DIR / "runs", ignore_errors=True)
|
|
|
|
|
|
def test_create_run_with_param_overrides() -> None:
|
|
"""验证创建任务时可携带 params 覆盖（如前端框选的 crop），并持久化。"""
|
|
with TestClient(app) as client:
|
|
workflow_id = _create_published_echo_workflow(client)
|
|
uploaded = client.post(
|
|
f"/api/apps/{workflow_id}/runs",
|
|
files={"file": ("sample.txt", b"x", "text/plain")},
|
|
data={"params": '{"step": {"crop": [0, 0.82, 1, 0.18]}}'},
|
|
)
|
|
assert uploaded.status_code == 200
|
|
run_id = uploaded.json()["id"]
|
|
run = client.get(f"/api/runs/{run_id}").json()
|
|
assert run["param_overrides"] == {"step": {"crop": [0, 0.82, 1, 0.18]}}
|
|
# 非法 JSON 返回 422。
|
|
bad = client.post(
|
|
f"/api/apps/{workflow_id}/runs",
|
|
files={"file": ("sample.txt", b"x", "text/plain")},
|
|
data={"params": "not-json"},
|
|
)
|
|
assert bad.status_code == 422
|
|
|
|
|
|
def test_create_run_params_non_object_rejected() -> None:
|
|
"""params 为 JSON 数组时返回 422。"""
|
|
with TestClient(app) as client:
|
|
workflow_id = _create_published_echo_workflow(client)
|
|
response = client.post(
|
|
f"/api/apps/{workflow_id}/runs",
|
|
files={"file": ("sample.txt", b"x", "text/plain")},
|
|
data={"params": "[1,2,3]"},
|
|
)
|
|
assert response.status_code == 422
|