fix: 防止任务删除误删源视频目录并跟踪审查问题

tests/test_run_deletion_safety.py

@@ -0,0 +1,104 @@
+"""任务删除安全回归：真实媒体副本验证用户目录与任务私有目录的归属边界。"""
+
+import shutil
+from pathlib import Path
+
+import pytest
+from fastapi.testclient import TestClient
+
+from wov_app.config import STORAGE_DIR
+from wov_app.main import app
+from wov_app.db import Database
+from wov_app.maintenance import OrphanCleaner
+
+
+@pytest.fixture
+def media_library(tmp_path):
+    """复制已有真实视频与字幕，任何删除只作用于测试临时目录。"""
+    assets = Path(__file__).resolve().parent.parent / "testdata"
+    sources = [assets / "subtitle_10s.mp4", assets / "ocr_srt_run_ac7f480a3ccb.srt"]
+    if not all(source.is_file() for source in sources):
+        pytest.skip("缺少真实视频或字幕测试素材")
+    library = tmp_path / "media"
+    library.mkdir()
+    files = [library / "movie.mp4", library / "movie.CN.srt"]
+    for source, target in zip(sources, files):
+        shutil.copy2(source, target)
+    return files, [path.read_bytes() for path in files]
+
+
+def _create_run(db, run_id, video, source, status):
+    """在真实数据库登记任务，不启动模型或调度器。"""
+    workflow_id = "delete-safety"
+    db.upsert_workflow({"id": workflow_id, "name": "删除安全回归"})
+    db.create_run({
+        "id": run_id, "workflow_id": workflow_id, "workflow_version": 1,
+        "source": source, "status": status, "input_uri": str(video),
+        "created_at": "2020-01-01T00:00:00+00:00",
+        "updated_at": "2020-01-01T00:00:00+00:00",
+    })
+    # 登记可读的真实字幕产物，拒绝删除时应连同记录保留。
+    db.create_artifact({
+        "run_id": run_id, "node_id": "ass", "name": "subtitle",
+        "uri": str(video.with_suffix(".CN.srt")), "mime_type": "application/x-subrip",
+    })
+
+
+@pytest.mark.parametrize("status", ["QUEUED", "RUNNING", "PAUSED", "FAILED", "COMPLETED"])
+def test_normal_delete_rejects_batch_run(media_library, status):
+    """普通 DELETE 对所有状态的批量 run 返回 422，保留媒体与关联数据。"""
+    files, contents = media_library
+    run_id = f"run_batch_delete_safety_{status.lower()}"
+    with TestClient(app) as client:
+        db = app.state.db
+        _create_run(db, run_id, files[0], "batch", status)
+        before = db.get_run(run_id)
+        artifacts = db.list_artifacts(run_id)
+        response = client.delete(f"/api/runs/{run_id}")
+        assert response.status_code == 422
+        assert "批量任务" in response.json()["detail"]
+        assert db.get_run(run_id) == before
+        assert db.list_artifacts(run_id) == artifacts
+        assert [path.read_bytes() for path in files] == contents
+
+
+def test_upload_delete_ignores_external_input_parent(media_library):
+    """历史上传记录即使指向外部视频，也仅清理按 run_id 定位的私有目录。"""
+    files, contents = media_library
+    run_id = "run_external_delete_safety"
+    with TestClient(app) as client:
+        db = app.state.db
+        _create_run(db, run_id, files[0], "upload", "FAILED")
+        private_dirs = [STORAGE_DIR / kind / run_id for kind in ("uploads", "runs")]
+        for directory in private_dirs:
+            directory.mkdir(parents=True)
+            shutil.copy2(files[1], directory / "subtitle.srt")
+        # 同级其他任务目录也不能被扩大范围删除。
+        sibling = STORAGE_DIR / "uploads" / "run_neighbor_delete_safety"
+        sibling.mkdir(parents=True)
+        shutil.copy2(files[1], sibling / "subtitle.srt")
+        response = client.delete(f"/api/runs/{run_id}")
+        assert response.status_code == 200
+        assert db.get_run(run_id) is None
+        assert db.list_artifacts(run_id) == []
+        assert [path.read_bytes() for path in files] == contents
+        assert all(not directory.exists() for directory in private_dirs)
+        assert (sibling / "subtitle.srt").read_bytes() == contents[1]
+
+
+def test_orphan_cleanup_ignores_external_input_parent(media_library, tmp_path):
+    """自动清理过期上传任务时也不能从 input_uri 推导递归删除范围。"""
+    files, contents = media_library
+    db = Database(tmp_path / "orphan.db")
+    run_id = "run_orphan_delete_safety"
+    _create_run(db, run_id, files[0], "upload", "COMPLETED")
+    # 产物确实丢失，符合孤儿清理条件；源视频与旁挂字幕仍是用户数据。
+    db.delete_run_artifacts(run_id)
+    storage = tmp_path / "private"
+    upload_dir = storage / "uploads" / run_id
+    upload_dir.mkdir(parents=True)
+    shutil.copy2(files[0], upload_dir / "movie.mp4")
+    OrphanCleaner(db, storage).clean_once()
+    assert db.get_run(run_id) is None
+    assert [path.read_bytes() for path in files] == contents
+    assert not upload_dir.exists()