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 +1,174 @@
+"""wov_sdk.models 的单元测试。
+
+测试覆盖所有数据模型的 JSON 往返序列化、字段校验和 manifest 文件加载，
+确保协议模型的稳定性。
+"""
+
+import json
+
+import pytest
+
+from wov_sdk.models import (
+    HealthResponse,
+    InvokeRequest,
+    InvokeResponse,
+    NodeManifest,
+    ProgressEvent,
+    WorkflowDefinition,
+    WorkflowEdge,
+    WorkflowNode,
+)
+
+
+def valid_manifest() -> NodeManifest:
+    """构造一个覆盖全部字段的合法 NodeManifest，供测试复用。"""
+    return NodeManifest(
+        id="echo",
+        name="Echo",
+        version="1.0.0",
+        capability="echo",
+        command=["python", "-m", "echo"],
+        repo_dir="wov-node-echo",
+        env={"PORT": "0"},
+        input_schema={"text": "string"},
+        output_schema={"text": "string"},
+        max_concurrency=2,
+        idle_ttl_seconds=15,
+        health_timeout_seconds=5,
+        keep_warm=True,
+    )
+
+
+def test_manifest_round_trip() -> None:
+    """验证 manifest 经过 to_dict/from_dict 后保持原值。"""
+    manifest = valid_manifest()
+    restored = NodeManifest.from_dict(manifest.to_dict())
+    assert restored == manifest
+
+
+@pytest.mark.parametrize(
+    ("field", "value"),
+    [
+        ("id", ""),
+        ("name", ""),
+        ("version", ""),
+        ("capability", ""),
+        ("repo_dir", ""),
+        ("command", []),
+        ("max_concurrency", 0),
+        ("idle_ttl_seconds", -1),
+        ("health_timeout_seconds", 0),
+    ],
+)
+def test_manifest_validation(field: str, value: object) -> None:
+    """验证必填字段为空或数值越界时抛出 ValueError。"""
+    manifest = valid_manifest()
+    setattr(manifest, field, value)
+    with pytest.raises(ValueError):
+        manifest.validate()
+
+
+def test_manifest_load(tmp_path) -> None:
+    """验证 NodeManifest.load 能从 JSON 文件读取并校验。"""
+    path = tmp_path / "node.manifest.json"
+    path.write_text(json.dumps(valid_manifest().to_dict()), encoding="utf-8")
+    loaded = NodeManifest.load(str(path))
+    assert loaded.id == "echo"
+
+
+def test_invoke_request_round_trip() -> None:
+    """验证 InvokeRequest 的 JSON 往返序列化。"""
+    request = InvokeRequest(
+        run_id="run_1",
+        node_instance_id="ni_1",
+        inputs={"text": "hello"},
+        params={"temperature": 0.2},
+        output_dir="out",
+    )
+    restored = InvokeRequest.from_dict(request.to_dict())
+    assert restored == request
+
+
+def test_invoke_response_round_trip() -> None:
+    """验证 InvokeResponse 的 JSON 往返序列化。"""
+    response = InvokeResponse(status="completed", outputs={"text": "hello"})
+    restored = InvokeResponse.from_dict(response.to_dict())
+    assert restored == response
+
+
+def test_health_and_progress_serialization() -> None:
+    """验证健康检查和进度事件模型的字典输出。"""
+    health = HealthResponse(status="ok", node_id="echo", version="1.0.0")
+    assert health.to_dict() == {
+        "status": "ok",
+        "node_id": "echo",
+        "version": "1.0.0",
+    }
+
+    progress = ProgressEvent(run_id="run_1", node_id="echo", progress=0.5, message="half")
+    assert progress.to_dict() == {
+        "run_id": "run_1",
+        "node_id": "echo",
+        "progress": 0.5,
+        "message": "half",
+    }
+
+
+def test_workflow_node_and_edge_round_trip() -> None:
+    """验证工作流节点与边的 JSON 往返序列化。"""
+    node = WorkflowNode(
+        id="asr",
+        node_type="faster-whisper",
+        params={"language": "ja"},
+        inputs={"audio_uri": "extract.audio_uri"},
+    )
+    edge = WorkflowEdge(from_node="extract", to_node="asr")
+    assert WorkflowNode.from_dict(node.to_dict()) == node
+    assert WorkflowEdge.from_dict(edge.to_dict()) == edge
+    assert edge.to_dict() == {"from": "extract", "to": "asr"}
+
+    assert node.to_dict()["inputs"] == {"audio_uri": "extract.audio_uri"}
+
+
+def test_workflow_definition_round_trip_and_validation() -> None:
+    """验证完整 DAG 定义可往返序列化并通过校验。"""
+    definition = WorkflowDefinition(
+        name="demo",
+        version=1,
+        nodes=[
+            WorkflowNode(id="extract", node_type="ffmpeg"),
+            WorkflowNode(id="asr", node_type="whisper"),
+        ],
+        edges=[WorkflowEdge(from_node="extract", to_node="asr")],
+        entry_inputs={"video_uri": "file"},
+        final_outputs={"srt": "asr.srt_uri"},
+    )
+    restored = WorkflowDefinition.from_dict(definition.to_dict())
+    assert restored == definition
+    restored.validate()
+
+
+def test_workflow_definition_invalid() -> None:
+    """验证非法 DAG（空名、版本为 0、重复节点、未知边）被拒绝。"""
+    with pytest.raises(ValueError):
+        WorkflowDefinition(name="", version=1).validate()
+
+    with pytest.raises(ValueError):
+        WorkflowDefinition(name="demo", version=0).validate()
+
+    duplicate = WorkflowDefinition(
+        name="demo",
+        version=1,
+        nodes=[WorkflowNode(id="a", node_type="x"), WorkflowNode(id="a", node_type="y")],
+    )
+    with pytest.raises(ValueError):
+        duplicate.validate()
+
+    unknown_edge = WorkflowDefinition(
+        name="demo",
+        version=1,
+        nodes=[WorkflowNode(id="a", node_type="x")],
+        edges=[WorkflowEdge(from_node="a", to_node="missing")],
+    )
+    with pytest.raises(ValueError):
+        unknown_edge.validate()