From 9c74f51b43437c3bc4517307c5d605f597b55444 Mon Sep 17 00:00:00 2001
From: starmen1265 <starmen1265@163.com>
Date: Mon, 16 Mar 2026 23:17:29 +0800
Subject: [PATCH] feat(05-02): add ArchiveInput and ArchiveOutput schemas

- Add ArchiveInput with content_dir, analysis_file, content_type fields
- Add ArchiveOutput with archive_file, skipped, platform fields
- Update PipelineConfig default steps to include archive step
---
 kb_pipeline/schemas.py | 39 +++++++++++++++++++++++++++++++++++++--
 1 file changed, 37 insertions(+), 2 deletions(-)

diff --git a/kb_pipeline/schemas.py b/kb_pipeline/schemas.py
index 8ab2318..83a3e02 100644
--- a/kb_pipeline/schemas.py
+++ b/kb_pipeline/schemas.py
@@ -397,15 +397,50 @@ class PipelineConfig(BaseModel):
     """Pipeline configuration
 
     Attributes:
-        steps: Steps to execute in order (default: parse, download, asr, analyze)
+        steps: Steps to execute in order (default: parse, download, asr, analyze, archive)
         output_dir: Base output directory
         skip_completed: Skip completed steps (default True)
         max_retries: Max retries per step (default 3)
     """
     steps: List[str] = Field(
-        default_factory=lambda: ["parse", "download", "asr", "analyze"],
+        default_factory=lambda: ["parse", "download", "asr", "analyze", "archive"],
         description="Steps to execute in order"
     )
     output_dir: Optional[Path] = Field(None, description="Base output directory")
     skip_completed: bool = Field(default=True, description="Skip completed steps")
     max_retries: int = Field(default=3, description="Max retries per step")
+
+
+# =============================================================================
+# Archive Schemas (Phase 5)
+# =============================================================================
+
+
+class ArchiveInput(StepInput):
+    """Archive 步骤输入
+
+    继承 StepInput 的基础字段，添加归档特定字段。
+
+    Attributes:
+        content_dir: 内容目录路径（中间目录）
+        analysis_file: 分析报告 md 文件路径
+        content_type: 内容类型
+    """
+    content_dir: str = Field(..., min_length=1, description="Content directory path (intermediate)")
+    analysis_file: str = Field(..., min_length=1, description="Path to analysis Markdown file")
+    content_type: str = Field(..., min_length=1, description="Content type (video, article, etc.)")
+
+
+class ArchiveOutput(StepOutput):
+    """Archive 步骤输出
+
+    继承 StepOutput 的基础字段，添加归档特定字段。
+
+    Attributes:
+        archive_file: 归档后的文件路径
+        skipped: 是否跳过（已有相同文件）
+        platform: 平台名称
+    """
+    archive_file: str = Field(default="", description="Path to archived file")
+    skipped: bool = Field(default=False, description="Whether archiving was skipped")
+    platform: str = Field(default="", description="Platform name")