feat: VRSub 单体应用（WOV 单机版）初始提交

为视频生成 VR 双眼字幕的单体实现：FastAPI 后端、调度器与全部节点（提音/转写/翻译/ASS/抽帧/OCR/LLM 过滤）在单进程内运行。 - 节点协议（wov_sdk 数据模型）与分布式版保持一致，预留回退桥梁 - 工作流即数据：DAG 存于 workflows/*.json，模型/链路改动只改数据 - 调度器：拓扑顺序执行、断点续跑（产物重建）、任务暂停/继续 - 抽帧按帧间隔（select 按帧号精确取帧），VLM OCR 与 LLM 过滤使用自适应线程池弹性并发，并打印数据处理速度进度日志 - 100% 行覆盖率（pytest --cov-fail-under=100）
2026-08-16 23:58:25 +08:00
commit 4746e0363f
75 changed files with 10969 additions and 0 deletions
@@ -0,0 +1,294 @@
+"""数据库层单元测试。
+
+直接对 Database 方法调用真实 SQLite 路径，覆盖工作流、版本、任务与产物的
+增删改查。节点注册表已改为进程内内存态，不再落库。
+"""
+
+from pathlib import Path
+
+from wov_app.db import Database
+
+
+def test_workflow_crud(tmp_path) -> None:
+    """验证工作流概要的插入、发布标记更新与删除。"""
+    db = Database(tmp_path / "wov.db")
+    workflow = {
+        "id": "demo",
+        "name": "Demo",
+        "description": "desc",
+        "published": 0,
+        "latest_version": 0,
+    }
+    db.upsert_workflow(workflow)
+    assert db.get_workflow("demo")["name"] == "Demo"
+    assert [item["id"] for item in db.list_workflows()] == ["demo"]
+
+    db.upsert_workflow({**workflow, "published": 1, "latest_version": 1})
+    assert db.get_workflow("demo")["published"] == 1
+
+    db.delete_workflow("demo")
+    assert db.get_workflow("demo") is None
+
+
+def test_workflow_versions(tmp_path) -> None:
+    """验证工作流版本的写入、最新版本查询与列表。"""
+    db = Database(tmp_path / "wov.db")
+    db.upsert_workflow(
+        {"id": "demo", "name": "Demo", "published": 1, "latest_version": 2}
+    )
+    definition = {"name": "Demo", "version": 1, "nodes": [], "edges": []}
+    db.create_workflow_version("demo", 1, definition)
+    db.create_workflow_version("demo", 2, {**definition, "version": 2})
+
+    latest = db.get_latest_workflow_version("demo")
+    assert latest["version"] == 2
+    assert latest["definition"]["version"] == 2
+
+    version = db.get_workflow_version("demo", 1)
+    assert version["version"] == 1
+    assert db.get_workflow_version("demo", 99) is None
+    assert len(db.list_workflow_versions("demo")) == 2
+
+    empty_db = Database(tmp_path / "empty.db")
+    assert empty_db.get_latest_workflow_version("missing") is None
+
+
+def test_run_and_artifact_crud(tmp_path) -> None:
+    """验证任务与产物的创建、查询、更新与删除。"""
+    db = Database(tmp_path / "wov.db")
+    db.upsert_workflow({"id": "demo", "name": "Demo", "published": 1, "latest_version": 1})
+    now = "2026-01-01T00:00:00+00:00"
+    db.create_run(
+        {
+            "id": "run_1",
+            "workflow_id": "demo",
+            "workflow_version": 1,
+            "status": "QUEUED",
+            "progress": 0,
+            "input_uri": "in.txt",
+            "created_at": now,
+            "updated_at": now,
+        }
+    )
+    assert db.get_run("run_1")["status"] == "QUEUED"
+    assert db.next_queued_run()["id"] == "run_1"
+
+    db.update_run("run_1", status="RUNNING", progress=0.5, updated_at=now)
+    db.update_run("run_1")
+    assert db.get_run("run_1")["status"] == "RUNNING"
+    assert db.get_run("run_1")["progress"] == 0.5
+    assert db.next_queued_run() is None
+    assert len(db.list_runs()) == 1
+
+    db.create_artifact(
+        {
+            "run_id": "run_1",
+            "node_id": "echo",
+            "name": "result",
+            "uri": "out.txt",
+            "mime_type": "text/plain",
+            "size": 3,
+        }
+    )
+    assert db.get_artifact("run_1", "result")["uri"] == "out.txt"
+    assert db.get_artifact("run_1", "missing") is None
+    assert len(db.list_artifacts("run_1")) == 1
+
+    db.delete_run_artifacts("run_1")
+    assert db.list_artifacts("run_1") == []
+
+
+def test_reset_run_clears_error_and_artifacts(tmp_path) -> None:
+    """验证 reset_run 会把失败任务恢复到排队状态并清空旧产物。"""
+    db = Database(tmp_path / "wov.db")
+    db.upsert_workflow({"id": "demo", "name": "Demo", "published": 1, "latest_version": 1})
+    now = "2026-01-01T00:00:00+00:00"
+    db.create_run(
+        {
+            "id": "run_1",
+            "workflow_id": "demo",
+            "workflow_version": 1,
+            "status": "FAILED",
+            "progress": 0.75,
+            "current_node_id": "translate",
+            "error": "timed out",
+            "input_uri": "in.txt",
+            "created_at": now,
+            "updated_at": now,
+        }
+    )
+    db.create_artifact(
+        {
+            "run_id": "run_1",
+            "node_id": "asr",
+            "name": "asr.srt_uri",
+            "uri": "out.srt",
+            "mime_type": "application/x-subrip",
+            "size": 3,
+        }
+    )
+
+    db.reset_run("run_1", "2026-01-02T00:00:00+00:00")
+
+    run = db.get_run("run_1")
+    assert run["status"] == "QUEUED"
+    assert run["progress"] == 0
+    assert run["current_node_id"] is None
+    assert run["error"] is None
+    assert run["updated_at"] == "2026-01-02T00:00:00+00:00"
+    assert run["created_at"] == now
+    assert db.list_artifacts("run_1") == []
+
+
+def test_delete_run(tmp_path) -> None:
+    """验证 delete_run 会删除任务记录及其产物记录。"""
+    db = Database(tmp_path / "wov.db")
+    db.upsert_workflow({"id": "demo", "name": "Demo", "published": 1, "latest_version": 1})
+    now = "2026-01-01T00:00:00+00:00"
+    db.create_run(
+        {
+            "id": "run_1",
+            "workflow_id": "demo",
+            "workflow_version": 1,
+            "status": "COMPLETED",
+            "progress": 1,
+            "input_uri": "in.txt",
+            "created_at": now,
+            "updated_at": now,
+        }
+    )
+    db.create_artifact(
+        {
+            "run_id": "run_1",
+            "node_id": "asr",
+            "name": "asr.srt_uri",
+            "uri": "out.srt",
+            "mime_type": "application/x-subrip",
+            "size": 3,
+        }
+    )
+    db.delete_run("run_1")
+    assert db.get_run("run_1") is None
+    assert db.list_artifacts("run_1") == []
+
+
+def test_list_run_ids(tmp_path) -> None:
+    """验证 list_run_ids 返回全部任务 ID，供孤儿清理对照使用。"""
+    db = Database(tmp_path / "wov.db")
+    db.upsert_workflow({"id": "demo", "name": "Demo", "published": 1, "latest_version": 1})
+    now = "2026-01-01T00:00:00+00:00"
+    assert db.list_run_ids() == []
+    for run_id in ("run_a", "run_b"):
+        db.create_run(
+            {
+                "id": run_id,
+                "workflow_id": "demo",
+                "workflow_version": 1,
+                "status": "QUEUED",
+                "progress": 0,
+                "created_at": now,
+                "updated_at": now,
+            }
+        )
+    assert set(db.list_run_ids()) == {"run_a", "run_b"}
+
+
+def test_run_param_overrides_persist(tmp_path) -> None:
+    """验证 param_overrides 随任务持久化并可读回。"""
+    db = Database(tmp_path / "wov.db")
+    db.upsert_workflow({"id": "demo", "name": "D", "published": 1, "latest_version": 1})
+    now = "2026-01-01T00:00:00+00:00"
+    db.create_run(
+        {
+            "id": "run_ov",
+            "workflow_id": "demo",
+            "workflow_version": 1,
+            "status": "QUEUED",
+            "progress": 0,
+            "param_overrides": {"extract": {"crop": [0, 0.5, 1, 0.5]}},
+            "created_at": now,
+            "updated_at": now,
+        }
+    )
+    run = db.get_run("run_ov")
+    assert run["param_overrides"] == {"extract": {"crop": [0, 0.5, 1, 0.5]}}
+    assert db.next_queued_run()["param_overrides"] == {"extract": {"crop": [0, 0.5, 1, 0.5]}}
+
+
+def test_db_migration_adds_param_overrides(tmp_path) -> None:
+    """旧库迁移：缺少 param_overrides 列的库打开后自动补列。"""
+    import sqlite3
+
+    db_path = tmp_path / "old.db"
+    conn = sqlite3.connect(db_path)
+    conn.execute(
+        "CREATE TABLE workflow_runs (id TEXT PRIMARY KEY, workflow_id TEXT NOT NULL,"
+        " workflow_version INTEGER NOT NULL, status TEXT NOT NULL, current_node_id TEXT,"
+        " progress REAL NOT NULL DEFAULT 0, error TEXT, input_uri TEXT,"
+        " created_at TEXT NOT NULL, updated_at TEXT NOT NULL)"
+    )
+    conn.commit()
+    conn.close()
+
+    Database(db_path)
+    conn = sqlite3.connect(db_path)
+    columns = [row[1] for row in conn.execute("PRAGMA table_info(workflow_runs)")]
+    conn.close()
+    assert "param_overrides" in columns
+
+
+def test_pause_resume_run(tmp_path) -> None:
+    """验证 pause_run/resume_run 的状态流转与 PAUSED 任务可被调度器取到。"""
+    db = Database(tmp_path / "wov.db")
+    db.upsert_workflow({"id": "demo", "name": "Demo", "published": 1, "latest_version": 1})
+    now = "2026-01-01T00:00:00+00:00"
+    db.create_run(
+        {
+            "id": "run_p",
+            "workflow_id": "demo",
+            "workflow_version": 1,
+            "status": "QUEUED",
+            "progress": 0,
+            "created_at": now,
+            "updated_at": now,
+        }
+    )
+    db.pause_run("run_p", now)
+    assert db.get_run("run_p")["status"] == "PAUSED"
+    # PAUSED 任务会被 next_queued_run 取到（等待续跑）。
+    assert db.next_queued_run()["id"] == "run_p"
+    db.resume_run("run_p", now)
+    assert db.get_run("run_p")["status"] == "QUEUED"
+    assert db.next_queued_run()["id"] == "run_p"
+
+
+def test_restore_run_outputs(tmp_path) -> None:
+    """验证从产物重建节点输出（断点续跑的依据）。"""
+    db = Database(tmp_path / "wov.db")
+    db.upsert_workflow({"id": "demo", "name": "Demo", "published": 1, "latest_version": 1})
+    now = "2026-01-01T00:00:00+00:00"
+    db.create_run(
+        {
+            "id": "run_r",
+            "workflow_id": "demo",
+            "workflow_version": 1,
+            "status": "PAUSED",
+            "progress": 0,
+            "created_at": now,
+            "updated_at": now,
+        }
+    )
+    db.create_artifact(
+        {
+            "run_id": "run_r",
+            "node_id": "extract",
+            "name": "frames_manifest",
+            "uri": "frames.json",
+            "mime_type": "application/json",
+            "size": 1,
+        }
+    )
+    assert db.restore_run_outputs("run_r") == {
+        "extract": {"frames_manifest": "frames.json"}
+    }
+    assert db.restore_run_outputs("run_none") == {}