kb_pipeline/schemas.py

@@ -273,3 +273,40 @@ class ParseOutput(StepOutput):
     content_id: str = Field(..., description="Extracted content ID")
     resolved_url: str = Field(..., description="Resolved URL after short link expansion")
     original_url: str = Field(..., description="Original URL provided by user")
+
+
+# =============================================================================
+# Download Schemas (Phase 04)
+# =============================================================================
+
+
+class DownloadInput(StepInput):
+    """Download 步骤输入
+
+    继承 StepInput 的基础字段，添加下载特定字段。
+
+    Attributes:
+        content_dir: 保存下载内容的目录路径
+        content_type: 内容类型 (video, article, answer, zhuanlan)
+    """
+    content_dir: str = Field(..., min_length=1, description="Directory to save downloaded content")
+    content_type: str = Field(..., min_length=1, description="Content type (video, article, answer, zhuanlan)")
+
+
+class DownloadOutput(StepOutput):
+    """Download 步骤输出
+
+    继承 StepOutput 的基础字段，添加下载特定字段。
+
+    Attributes:
+        metadata_file: 元数据 JSON 文件路径
+        content_file: 内容文件路径 (视频/音频或文本)
+        title: 内容标题
+        author: 内容作者
+        duration: 视频内容的时长（秒），仅视频有值
+    """
+    metadata_file: str = Field(..., description="Path to metadata JSON file")
+    content_file: str = Field(..., description="Path to content file (video/audio or text)")
+    title: str = Field(..., description="Content title")
+    author: str = Field(..., description="Content author")
+    duration: Optional[int] = Field(None, description="Duration for video content in seconds")