Skip to content

RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.

fix(ingestion): add process_end_at column and keep OSS ingest-log a no-op (#21888)

xugangqiangf3be804337d4
diff --git a/internal/dao/ingestion_log_process_end_at_test.go b/internal/dao/ingestion_log_process_end_at_test.go
new file mode 100644
index 0000000000..6083645b90
--- /dev/null
+++ b/internal/dao/ingestion_log_process_end_at_test.go
@@ -0,0 +1,64 @@
+// Copyright 2026 The InfiniFlow Authors. All Rights Reserved.
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+// http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+package dao
+
+import (
+ "context"
+ "testing"
+
+ "ragflow/internal/entity"
+
+ "github.com/glebarez/sqlite"
+ "gorm.io/gorm"
+)
+
+// TestMigrateIngestionLogRunIdentityAddsProcessEndAt is a regression test for the
+// missing schema migration in #21711: the PR added PipelineOperationLog.ProcessEndAt
+// (column process_end_at) and persists it on terminal settlement, but omitted the
+// ALTER that adds the column. Without it, every enqueue fails with
+// "Unknown column 'process_end_at' in 'field list'".
+func TestMigrateIngestionLogRunIdentityAddsProcessEndAt(t *testing.T) {
+ db, err := gorm.Open(sqlite.Open(":memory:"), &gorm.Config{})
+ if err != nil {
+ t.Fatalf("open sqlite: %v", err)
+ }
+ ctx := context.Background()
+ if err := db.Exec(`CREATE TABLE pipeline_operation_log (
+ id varchar(32) PRIMARY KEY,
+ document_id varchar(32) NOT NULL
+ )`).Error; err != nil {
+ t.Fatalf("create legacy table: %v", err)
+ }
+
+ if err := migrateIngestionLogRunIdentity(ctx, db); err != nil {
+ t.Fatalf("migrateIngestionLogRunIdentity: %v", err)
+ }
+
+ migrator := db.Migrator()
+ if !migrator.HasColumn(&entity.PipelineOperationLog{}, "process_end_at") {
+ t.Fatal("pipeline_operation_log missing process_end_at column after migration")
+ }
+ if !migrator.HasIndex(&entity.PipelineOperationLog{}, "idx_pipeline_operation_log_process_end_at") {
+ t.Fatal("pipeline_operation_log missing process_end_at index after migration")
+ }
+
+ // Idempotent: a second run must not error and must keep the column.
+ if err := migrateIngestionLogRunIdentity(ctx, db); err != nil {
+ t.Fatalf("second migrateIngestionLogRunIdentity: %v", err)
+ }
+ if !migrator.HasColumn(&entity.PipelineOperationLog{}, "process_end_at") {
+ t.Fatal("process_end_at column lost after second migration")
+ }
+}
diff --git a/internal/dao/migration.go b/internal/dao/migration.go
index 52c87122c1..17d6e22f4a 100644
--- a/internal/dao/migration.go
+++ b/internal/dao/migration.go
@@ -447,6 +447,16 @@ func migrateIngestionLogRunIdentity(ctx context.Context, db *gorm.DB) error {
return fmt.Errorf("add pipeline_operation_log.run_count: %w", err)
}
}
+ if !migrator.HasColumn(&entity.PipelineOperationLog{}, "process_end_at") {
+ if err := db.WithContext(ctx).Exec(
+ "ALTER TABLE pipeline_operation_log ADD COLUMN process_end_at datetime NULL",
+ ).Error; err != nil && !isDuplicateColumnError(err) {
+ return fmt.Errorf("add pipeline_operation_log.process_end_at: %w", err)
+ }
+ }
+ if err := createIngestionLogIndexIfMissing(migrator, &entity.PipelineOperationLog{}, "idx_pipeline_operation_log_process_end_at", "add pipeline_operation_log.process_end_at index"); err != nil {
+ return err
+ }
if err := createIngestionLogIndexIfMissing(migrator, &entity.PipelineOperationLog{}, "idx_pipeline_operation_log_document_run", "add pipeline_operation_log document/run index"); err != nil {
return err
}