From 51644997e480bb361886c07534e7fac2d740e01b Mon Sep 17 00:00:00 2001
From: starmen1265 <starmen1265@163.com>
Date: Fri, 13 Mar 2026 23:28:30 +0800
Subject: [PATCH] feat(04-03): add AnalyzeInput and AnalyzeOutput schemas

- AnalyzeInput extends StepInput with metadata_file, content_file, content_type, output_file
- AnalyzeOutput extends StepOutput with analysis_file, summary, main_topics, key_insights, tags, stats
- Supports both video and article content types

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---
 kb_pipeline/schemas.py | 43 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 43 insertions(+)

diff --git a/kb_pipeline/schemas.py b/kb_pipeline/schemas.py
index 6260edd..e05aa7b 100644
--- a/kb_pipeline/schemas.py
+++ b/kb_pipeline/schemas.py
@@ -310,3 +310,46 @@ class DownloadOutput(StepOutput):
     title: str = Field(..., description="Content title")
     author: str = Field(..., description="Content author")
     duration: Optional[int] = Field(None, description="Duration for video content in seconds")
+
+
+# =============================================================================
+# Analyze Schemas (Phase 04)
+# =============================================================================
+
+
+class AnalyzeInput(StepInput):
+    """Analyze 步骤输入
+
+    继承 StepInput 的基础字段，添加分析特定字段。
+
+    Attributes:
+        metadata_file: 元数据 JSON 文件路径
+        content_file: 内容文件路径（字幕 JSON 或文章内容）
+        content_type: 内容类型（video 或 article）
+        output_file: 输出分析 Markdown 文件路径
+    """
+    metadata_file: str = Field(..., min_length=1, description="Path to metadata JSON file")
+    content_file: str = Field(..., min_length=1, description="Path to content file (subtitle JSON or article content)")
+    content_type: str = Field(..., min_length=1, description="Content type (video or article)")
+    output_file: str = Field(..., min_length=1, description="Path to output analysis Markdown file")
+
+
+class AnalyzeOutput(StepOutput):
+    """Analyze 步骤输出
+
+    继承 StepOutput 的基础字段，添加分析特定字段。
+
+    Attributes:
+        analysis_file: 生成的分析报告文件路径
+        summary: 内容摘要
+        main_topics: 提取的主要主题列表
+        key_insights: 关键见解列表
+        tags: 推荐标签列表
+        stats: 分析统计信息字典
+    """
+    analysis_file: str = Field(..., description="Path to generated analysis report")
+    summary: str = Field(default="", description="Content summary")
+    main_topics: List[str] = Field(default_factory=list, description="Main topics extracted")
+    key_insights: List[str] = Field(default_factory=list, description="Key insights")
+    tags: List[str] = Field(default_factory=list, description="Recommended tags")
+    stats: Dict[str, Any] = Field(default_factory=dict, description="Statistics about analysis")