fix(data-process): 发布精确三路数据切分

backend/app/modules/data_process/algorithms.py

@@ -2871,6 +2871,51 @@ def stable_split(
     return "test"
 
 
+def stable_split_assignments(
+    values: Sequence[str | int],
+    split: Mapping[str, int] | None = None,
+    *,
+    seed: str = "",
+) -> list[DatasetSplit]:
+    """按稳定顺序和精确配额批量划分数据集。
+
+    单条哈希分桶只能在大样本下近似比例。这里先按哈希稳定排序，再用
+    最大余数法计算各切分配额，确保小数据集也严格遵循配置比例。
+    """
+
+    ratios = dict(split or {"train": 80, "validation": 10, "test": 10})
+    # 复用单条划分的参数校验，避免两套规则逐渐漂移。
+    stable_split("validation", ratios, seed=seed)
+    if not values:
+        return []
+
+    split_order: tuple[DatasetSplit, ...] = ("train", "validation", "test")
+    exact = {name: len(values) * ratios[name] / 100 for name in split_order}
+    quotas = {name: math.floor(exact[name]) for name in split_order}
+    remaining = len(values) - sum(quotas.values())
+    remainder_order = sorted(
+        split_order,
+        key=lambda name: (-(exact[name] - quotas[name]), split_order.index(name)),
+    )
+    for name in remainder_order[:remaining]:
+        quotas[name] += 1
+
+    ranked_indices = sorted(
+        range(len(values)),
+        key=lambda index: (
+            hashlib.sha256(f"{seed}:{values[index]}".encode("utf-8")).digest(),
+            index,
+        ),
+    )
+    assignments: list[DatasetSplit] = ["train"] * len(values)
+    cursor = 0
+    for name in split_order:
+        for index in ranked_indices[cursor : cursor + quotas[name]]:
+            assignments[index] = name
+        cursor += quotas[name]
+    return assignments
+
+
 def _preview_content(item: Mapping[str, Any]) -> str:
     for field in ("edited_content", "editedContent", "original_content", "originalContent", "content"):
         value = item.get(field)
@@ -2970,9 +3015,16 @@ def generate_standard_records(
                     "original_input": input_text,
                     "original_output": output,
                     "status": status,
-                    "split": stable_split(result_id, split, seed=split_seed),
+                    "split": "train",
                 }
             )
+    assignments = stable_split_assignments(
+        [str(result["id"]) for result in results],
+        split,
+        seed=split_seed,
+    )
+    for result, assignment in zip(results, assignments, strict=True):
+        result["split"] = assignment
     return results
 
 
@@ -3021,4 +3073,5 @@ __all__ = [
     "remove_document_noise",
     "score_quality",
     "stable_split",
+    "stable_split_assignments",
 ]