feat(annotation): 添加文本分段标注功能

- 引入文本分割器实现长文本按200字符自动分段
- 增加分段状态管理和段落导航界面
- 支持按段落保存和加载标注数据
- 实现分段模式下的标注状态跟踪
- 扩展API接口支持段落索引参数
- 添加分段相关的数据模型定义

runtime/datamate-python/app/module/annotation/schema/editor.py

@@ -51,12 +51,30 @@ class EditorTaskListResponse(BaseModel):
     model_config = ConfigDict(populate_by_name=True)
 
 
+class SegmentInfo(BaseModel):
+    """段落信息（用于文本分段标注）"""
+
+    idx: int = Field(..., description="段落索引")
+    text: str = Field(..., description="段落文本")
+    start: int = Field(..., description="在原文中的起始位置")
+    end: int = Field(..., description="在原文中的结束位置")
+    has_annotation: bool = Field(False, alias="hasAnnotation", description="该段落是否已有标注")
+
+    model_config = ConfigDict(populate_by_name=True)
+
+
 class EditorTaskResponse(BaseModel):
     """编辑器任务详情（可直接喂给 Label Studio Editor 的 task 对象）"""
 
     task: Dict[str, Any] = Field(..., description="Label Studio task 对象")
     annotation_updated_at: Optional[datetime] = Field(None, alias="annotationUpdatedAt", description="标注更新时间")
 
+    # 分段相关字段
+    segmented: bool = Field(False, description="是否启用分段模式")
+    segments: Optional[List[SegmentInfo]] = Field(None, description="段落列表")
+    total_segments: int = Field(0, alias="totalSegments", description="总段落数")
+    current_segment_index: int = Field(0, alias="currentSegmentIndex", description="当前段落索引")
+
     model_config = ConfigDict(populate_by_name=True)
 
 
@@ -69,6 +87,12 @@ class UpsertAnnotationRequest(BaseModel):
         alias="expectedUpdatedAt",
         description="乐观锁：若提供则要求与当前记录 updated_at 一致，否则返回 409",
     )
+    # 分段保存支持
+    segment_index: Optional[int] = Field(
+        None,
+        alias="segmentIndex",
+        description="段落索引（分段模式下必填）",
+    )
 
     model_config = ConfigDict(populate_by_name=True)