feat: 平台治理与对象存储增强，审批中心与运行日志整合

- 新增 storage/policy.py 落盘策略：按大小/类型决定文件存 MinIO 或内联数据库
- 数据处理源文件与生成结果写入 MinIO 并登记 storage_objects，支持失败回滚
- 算力节点训练产物按版本归档到 MinIO，登记 model_artifacts
- 数据转换任务输入输出对象化，支持从 MinIO 读写
- 新增审批中心（申请/我的/策略）、组织与权限、运行日志整合页面
- schema 与 docker 配置、前端路由侧边栏、治理文档同步更新

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

backend/app/modules/data_process/store/datasets.py

@@ -11,6 +11,7 @@ import psycopg
 
 from app.core.config import get_settings
 from app.modules.storage.minio_store import get_object_storage
+from app.modules.storage.policy import should_store_in_minio
 
 from .base import (
     StoreBase,
@@ -168,7 +169,11 @@ class DatasetsMixin:
                 split_name: assignments.count(split_name) for split_name in split_order
             }
             split_specs: list[dict[str, Any]] = []
-            use_minio = bool(get_settings().minio_enabled)
+            # Explicit local is retained for old callers/tests that request the
+            # legacy backend; all normal platform requests default to MinIO.
+            allow_minio = bool(get_settings().minio_enabled) and str(
+                payload.get("storage_type") or "minio"
+            ).lower() != "local"
             for split_name in split_order:
                 split_records = [
                     (source_row, record)
@@ -193,12 +198,15 @@ class DatasetsMixin:
                         "storage_object_id": (
                             f"db://data-process/{task_id}/{file_id}/v1"
                         ),
+                        "store_in_minio": allow_minio and should_store_in_minio(
+                            len(raw), content_type="application/jsonl", file_format="jsonl"
+                        ),
                     }
                 )
             source_result_ids = [row["id"] for row in rows]
             common_metadata = {
                 "source": "data_process",
-                "storage_backend": "minio" if use_minio else "database",
+                "storage_backend": "minio" if any(spec["store_in_minio"] for spec in split_specs) else "database",
                 "source_task_id": task_id,
                 "output_type": _task_output_type(task),
                 "reasoning_detail": _task_reasoning_detail(task),
@@ -273,7 +281,7 @@ class DatasetsMixin:
                     split_name = str(spec["split"])
                     dataset_id = dataset_ids[split_name]
                     storage_object_id = str(spec["storage_object_id"])
-                    if use_minio:
+                    if spec["store_in_minio"]:
                         file_name = f"{base_dataset_name}.{split_name}.jsonl"
                         object_key = f"datasets/{dataset_id}/versions/{spec['version_id']}/{file_name}"
                         uploaded = get_object_storage().put_bytes(
@@ -356,7 +364,7 @@ class DatasetsMixin:
                             (
                                 dataset_name,
                                 dataset_types[split_name],
-                                "minio" if use_minio else (payload.get("storage_type") or "local"),
+                        "minio" if spec["store_in_minio"] else "database",
                                 f"{len(spec['raw'])} B",
                                 len(spec["raw"]),
                                 len(spec["records"]),
@@ -386,7 +394,7 @@ class DatasetsMixin:
                                 dataset_id,
                                 dataset_name,
                                 dataset_types[split_name],
-                                "minio" if use_minio else (payload.get("storage_type") or "local"),
+                                "minio" if spec["store_in_minio"] else "database",
                                 task_id,
                                 task_id,
                                 f"{len(spec['raw'])} B",
@@ -405,7 +413,11 @@ class DatasetsMixin:
                             ),
                         ).fetchone()
 
-                    file_metadata = {**dataset_metadata, "file_split": split_name}
+                    file_metadata = {
+                        **dataset_metadata,
+                        "file_split": split_name,
+                        "storage_backend": "minio" if spec["store_in_minio"] else "database",
+                    }
                     version = {
                         "id": spec["version_id"],
                         "version_no": 1,