refactor : pipeline 策略化拆分，消除 _flush if/else

- PackingStrategy / PositionIdStrategy / StoreWriter 独立文件 + Factory
- Pipeline._flush 零 if/else，纯编排
- SectionRenderer 从 SectionedMaskBuilder 分离
- OutputConfig.position_ids_mode 默认改为 ""none""

astrai/preprocessing/position_id.py

@@ -0,0 +1,50 @@
+"""Position-id generation strategies for packed sequences.
+
+Each strategy takes the list of per-document token sequences after packing
+and returns a flat list of position ids (same total length as all
+sequences combined).  The pipeline wraps the result into a tensor and
+attaches it as ``position_ids``.
+"""
+
+from abc import ABC, abstractmethod
+from typing import List
+
+from astrai.factory import BaseFactory
+
+
+class PositionIdStrategy(ABC):
+    """Generate ``position_ids`` for packed sequences."""
+
+    @abstractmethod
+    def generate(self, sequences: List[list]) -> List[int]: ...
+
+
+class PositionIdStrategyFactory(BaseFactory["PositionIdStrategy"]):
+    @classmethod
+    def _validate_component(cls, component_cls: type):
+        if not issubclass(component_cls, PositionIdStrategy):
+            raise TypeError(
+                f"{component_cls.__name__} must inherit from PositionIdStrategy"
+            )
+
+
+@PositionIdStrategyFactory.register("none")
+class NoPositionId(PositionIdStrategy):
+    def generate(self, sequences):
+        return []
+
+
+@PositionIdStrategyFactory.register("doc_reset")
+class DocResetPositionId(PositionIdStrategy):
+    def generate(self, sequences):
+        pos_ids = []
+        for seq in sequences:
+            pos_ids.extend(range(len(seq)))
+        return pos_ids
+
+
+@PositionIdStrategyFactory.register("continuous")
+class ContinuousPositionId(PositionIdStrategy):
+    def generate(self, sequences):
+        total = sum(len(seq) for seq in sequences)
+        return list(range(total))