feat(04-01): add ParseInput and ParseOutput schemas

- ParseInput extends StepInput with url field
- ParseOutput extends StepOutput with platform, content_type, content_id, resolved_url, original_url
- Tests for schema validation and inheritance

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

kb_pipeline/schemas.py

@@ -233,3 +233,43 @@ class ASROutput(StepOutput):
     speakers: Optional[List[str]] = Field(
         None, description="说话者列表（仅说话者分离时有值）"
     )
+
+
+# =============================================================================
+# Parse Schemas (Phase 04)
+# =============================================================================
+
+
+class ParseInput(StepInput):
+    """Parse 步骤输入
+
+    继承 StepInput 的基础字段，添加 URL 字段。
+    content_id 和 platform 在解析前是空的，解析后会被填充。
+
+    Attributes:
+        url: 要解析的 URL
+        content_id: 解析后填充的内容 ID（初始为空）
+        platform: 解析后填充的平台名称（初始为空）
+    """
+    url: str = Field(..., min_length=1, description="URL to parse")
+    content_id: str = Field(default="", description="Will be populated after parsing")
+    platform: str = Field(default="", description="Will be populated after parsing")
+
+
+class ParseOutput(StepOutput):
+    """Parse 步骤输出
+
+    继承 StepOutput 的基础字段，添加解析特定字段。
+
+    Attributes:
+        platform: 检测到的平台 (bilibili, zhihu)
+        content_type: 内容类型 (video, article, answer, zhuanlan)
+        content_id: 提取的内容 ID
+        resolved_url: 短链解析后的完整 URL
+        original_url: 用户提供的原始 URL
+    """
+    platform: str = Field(..., description="Detected platform")
+    content_type: str = Field(..., description="Content type (video, article, etc.)")
+    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")