fix(data-process): 保留重新生成前的已发布数据集

backend/app/modules/data_process/store.py

@@ -174,6 +174,7 @@ def _decode_row(row: dict[str, Any] | None) -> dict[str, Any] | None:
         "metadata": {},
         "quality_score": {},
         "versions": [],
+        "output_datasets": [],
     }.items():
         if key in item:
             item[key] = _json_value(item[key], default)
@@ -318,7 +319,12 @@ class DataProcessStore:
                            ) ORDER BY CASE dataset.type
                                WHEN 'train' THEN 1 WHEN 'val' THEN 2 WHEN 'test' THEN 3 ELSE 4 END), '[]'::json)
                             FROM datasets dataset
-                            WHERE dataset.source_task_id=task.id AND dataset.source='task')
+                            WHERE dataset.source='task'
+                              AND dataset.deleted_at IS NULL
+                              AND (
+                                  dataset.source_task_id=task.id
+                                  OR (dataset.source_task_id IS NULL AND dataset.task_id=task.id)
+                              ))
                              AS output_datasets,
                            CASE
                              WHEN task.started_at IS NOT NULL AND task.completed_at IS NOT NULL
@@ -459,14 +465,30 @@ class DataProcessStore:
                     current_config,
                     next_config,
                 )
+                now = utcnow()
+                # 002 迁移前发布的数据集只有 task_id。先补齐新关联字段，保证
+                # 解除任务输出指针后，详情和后续重新发布仍能定位原来的三份数据集。
+                conn.execute(
+                    """
+                    UPDATE datasets
+                    SET source_task_id=%s, updated_at=%s
+                    WHERE source='task' AND source_task_id IS NULL AND task_id=%s
+                      AND deleted_at IS NULL
+                    """,
+                    (task_id, now, task_id),
+                )
                 published_row = conn.execute(
                     """
                     SELECT EXISTS(
                         SELECT 1 FROM datasets
-                        WHERE source_task_id=%s AND source='task'
+                        WHERE source='task' AND deleted_at IS NULL
+                          AND (
+                              source_task_id=%s
+                              OR (source_task_id IS NULL AND task_id=%s)
+                          )
                     ) AS exists
                     """,
-                    (task_id,),
+                    (task_id, task_id),
                 ).fetchone()
                 published_outputs_preserved = bool(task.get("output_dataset_id")) or bool(
                     published_row and published_row.get("exists")
@@ -493,7 +515,6 @@ class DataProcessStore:
                     ).fetchone()
                     preview_count = int((preview_row or {}).get("count") or 0)
 
-                now = utcnow()
                 row = conn.execute(
                     """
                     UPDATE data_process_tasks
@@ -1460,10 +1481,14 @@ class DataProcessStore:
             existing_datasets = conn.execute(
                 """
                 SELECT * FROM datasets
-                WHERE source_task_id=%s AND source='task'
+                WHERE source='task' AND deleted_at IS NULL
+                  AND (
+                      source_task_id=%s
+                      OR (source_task_id IS NULL AND task_id=%s)
+                  )
                 ORDER BY created_at, id
                 """,
-                (task_id,),
+                (task_id, task_id),
             ).fetchall()
             existing_by_split: dict[str, dict[str, Any]] = {}
             primary_existing = None