refactor : 统一 SectionedMaskBuilder，支持可配置 dtype

- 三合一 MaskBuilder，移除 chat/instruction/text，统一为 sections 配置
- OutputConfig 增加 dtype 字段 (per-key，默认 int32)
- 移除 from __future__ import annotations
- 测试适配新配置格式

astrai/config/preprocess_config.py

@@ -1,20 +1,14 @@
 """Pipeline configuration for JSONL preprocessing."""
 
-from __future__ import annotations
-
 from dataclasses import dataclass, field
-from typing import Dict, Optional
+from typing import Dict, List, Optional
 
 from astrai.config.base import BaseConfig
 
 
 @dataclass
 class InputConfig(BaseConfig):
-    type: str = "chat"
-    messages_key: str = "messages"
-    prompt_key: str = "prompt"
-    response_key: str = "response"
-    text_key: str = "text"
+    sections: Optional[List[Dict]] = None
 
 
 @dataclass
@@ -31,6 +25,7 @@ class OutputConfig(BaseConfig):
     domain_key: Optional[str] = None
     storage_format: str = "bin"
     max_tokens_per_shard: int = 100_000_000
+    dtype: Dict[str, str] = field(default_factory=dict)
 
 
 @dataclass