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/api/v1/endpoints/data_process.py

@@ -35,6 +35,8 @@ from fastapi.responses import StreamingResponse
 from psycopg.rows import dict_row
 
 from app.core.auth import filter_accessible_resource_ids, get_current_user, is_admin
+from app.core.config import get_settings
+from app.db.platform_store import get_platform_store
 from app.modules.data_process.algorithms import (
     ParsedText,
     canonical_record_json,
@@ -85,6 +87,8 @@ from app.modules.data_process.store import (
     new_id,
     repeat_task_id,
 )
+from app.modules.storage.minio_store import get_object_storage
+from app.modules.storage.policy import should_store_in_minio
 from app.schemas.data_process import (
     DataProcessRegenerateRequest,
     DataProcessRepeatRequest,
@@ -224,9 +228,38 @@ def _commit_source_batch(
     staged: list[StagedSourceObject],
 ) -> list[dict[str, Any]]:
     storage.publish(staged)
+    storage_object_ids: list[str] = []
     try:
+        # The source reference remains in the task schema for compatibility,
+        # while storage_objects provides the authoritative MinIO index.
+        if get_settings().minio_enabled:
+            for item in prepared:
+                reference = str(item.get("storage_object_id") or "")
+                if not reference.startswith("minio://"):
+                    continue
+                object_key = storage.object_key(reference)
+                metadata = get_object_storage().stat(object_key)
+                object_row = get_platform_store().create_storage_object({
+                    "resource_type": "data_process_source",
+                    "resource_id": task_id,
+                    "version_id": str(item.get("id") or new_id("dpsf")),
+                    "bucket": get_object_storage().bucket,
+                    "object_key": object_key,
+                    "file_name": item.get("name"),
+                    "content_type": (item.get("metadata") or {}).get("content_type", "application/octet-stream"),
+                    "byte_size": metadata.get("byte_size") or item.get("raw_size") or 0,
+                    "checksum_sha256": item.get("checksum_sha256"),
+                    "status": "available",
+                    "created_by": item.get("created_by"),
+                })
+                storage_object_ids.append(str(object_row["id"]))
         return store.add_source_files(task_id, prepared)
     except Exception:
+        for object_id in storage_object_ids:
+            try:
+                get_platform_store().update_storage_object(object_id, {"status": "deleted"})
+            except Exception:
+                pass
         for item in staged:
             try:
                 storage.delete(item.reference)
@@ -774,6 +807,25 @@ def _run_generation(
                 duplicate_count=duplicate_count,
                 error_count=error_count,
             )
+            result_bytes = "".join(
+                structured_json_dumps(item) + "\n" for item in accepted
+            ).encode("utf-8")
+            if should_store_in_minio(len(result_bytes)):
+                result_key = f"data-process/{task_id}/results/{generation_run_id}.jsonl"
+                uploaded = get_object_storage().put_bytes(result_key, result_bytes, "application/jsonl")
+                get_platform_store().create_storage_object({
+                    "resource_type": "data_process_result",
+                    "resource_id": task_id,
+                    "version_id": generation_run_id,
+                    "bucket": uploaded["bucket"],
+                    "object_key": result_key,
+                    "file_name": f"{generation_run_id}.jsonl",
+                    "content_type": "application/jsonl",
+                    "byte_size": len(result_bytes),
+                    "checksum_sha256": hashlib.sha256(result_bytes).hexdigest(),
+                    "status": "available",
+                    "created_by": (store.get_task(task_id) or {}).get("created_by"),
+                })
             logger.info(
                 "data process generation completed task_id=%s generation_run_id=%s "
                 "output_count=%s filtered_count=%s duplicate_count=%s error_count=%s "
@@ -933,7 +985,7 @@ def _repeat_file_copies(
         source = store.get_source_file(source_task_id, old_file_id, include_content=True)
         new_file_id = new_id("dpsf")
         old_reference = str(source.get("storage_object_id") or "")
-        if old_reference.startswith("local://data-process/"):
+        if old_reference.startswith(("local://data-process/", "minio://data-process/")):
             staged_object = storage.stage_copy(
                 batch_id=batch_id,
                 source_reference=old_reference,