lobehub/tests/openapi/knowledge-base-delete.test.ts
Innei 3b81a94d76
🐛 fix(kb): clean up vector storage when deleting knowledge bases (#13254)
* 🐛 feat(db): add findExclusiveFileIds, deleteWithFiles, deleteAllWithFiles to KnowledgeBaseModel

Add methods to safely clean up vector storage when deleting knowledge bases:
- findExclusiveFileIds: identifies files belonging only to a specific KB
- deleteWithFiles: deletes KB and its exclusive files with chunks/embeddings
- deleteAllWithFiles: bulk version for deleting all user KBs

* 🐛 fix(kb): wire vector cleanup in TRPC router, OpenAPI service, and client

- TRPC removeKnowledgeBase: use deleteWithFiles when removeFiles=true + S3 cleanup
- TRPC removeAllKnowledgeBases: use deleteAllWithFiles + S3 cleanup
- OpenAPI deleteKnowledgeBase: use deleteWithFiles + S3 cleanup
- Client service: default removeFiles=true when deleting knowledge base

* 🐛 fix(knowledgeBase): change default behavior of deleteKnowledgeBase to not remove files and update related tests

Signed-off-by: Innei <tukon479@gmail.com>

*  feat(knowledgeBase): add optional query parameter to deleteKnowledgeBase for file removal

- Introduced `removeFiles` query parameter to control the deletion of exclusive files and derived data when deleting a knowledge base.
- Updated `KnowledgeBaseController`, `KnowledgeBaseService`, and related schemas to support this new functionality.

This change enhances the flexibility of the delete operation, allowing users to choose whether to remove associated files.

Signed-off-by: Innei <tukon479@gmail.com>

* 🐛 fix: cascade knowledge base deletion and add orphan cleanup runbook

*  feat(knowledgeRepo): implement cascading deletion for file-backed documents

- Enhanced the `KnowledgeRepo` to ensure that when a document with an associated file is deleted, all related data (files, chunks, embeddings) are also removed.
- Introduced a new method `deleteDocumentWithRelations` to handle the cascading deletion logic.
- Updated tests to verify that all related entities are deleted when a file-backed document is removed.

This change improves data integrity by ensuring that no orphaned records remain after deletions.

Signed-off-by: Innei <tukon479@gmail.com>

* Defer DocumentService file initialization

* Fix flaky database tests and knowledge repo fixtures

* Add deletion regression tests for folders and external files

*  chore: remove kb orphan cleanup files from pr

---------

Signed-off-by: Innei <tukon479@gmail.com>
2026-04-10 01:56:05 +08:00

95 lines
2.7 KiB
TypeScript

import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
import type { LobeChatDatabase } from '@/database/type';
import { FileService } from '@/server/services/file';
import { KnowledgeBaseService } from '../../packages/openapi/src/services/knowledge-base.service';
vi.mock('@/server/services/file');
describe('KnowledgeBaseService.deleteKnowledgeBase', () => {
let db: LobeChatDatabase;
let deleteFilesSpy: ReturnType<typeof vi.fn>;
beforeEach(() => {
db = {
query: {
knowledgeBases: {
findFirst: vi.fn().mockResolvedValue({ id: 'kb-1', userId: 'user-1' }),
},
},
} as unknown as LobeChatDatabase;
deleteFilesSpy = vi.fn().mockResolvedValue(undefined);
vi.mocked(FileService).mockImplementation(() => ({ deleteFiles: deleteFilesSpy }) as any);
});
afterEach(() => {
vi.restoreAllMocks();
});
const createService = () => {
const service = new KnowledgeBaseService(db, 'user-1');
vi.spyOn(service as any, 'log').mockImplementation(() => {});
vi.spyOn(service as any, 'resolveOperationPermission').mockResolvedValue({
isPermitted: true,
message: '',
});
return service;
};
it('should always delete exclusive files together with the knowledge base', async () => {
const service = createService();
const deleteWithFilesSpy = vi.fn().mockResolvedValue({
deletedFiles: [],
});
Reflect.set(service, 'knowledgeBaseModel', {
deleteWithFiles: deleteWithFilesSpy,
});
await expect(service.deleteKnowledgeBase('kb-1')).resolves.toEqual({
message: 'Knowledge base deleted successfully',
success: true,
});
expect(deleteWithFilesSpy).toHaveBeenCalledWith('kb-1');
});
it('should delete external files when deleted knowledge-base files have URLs', async () => {
const service = createService();
Reflect.set(service, 'knowledgeBaseModel', {
deleteWithFiles: vi.fn().mockResolvedValue({
deletedFiles: [
{ id: 'file-1', url: 'https://example.com/a.pdf' },
{ id: 'file-2', url: null },
{ id: 'file-3', url: 'https://example.com/b.pdf' },
],
}),
});
await service.deleteKnowledgeBase('kb-1');
expect(deleteFilesSpy).toHaveBeenCalledWith([
'https://example.com/a.pdf',
'https://example.com/b.pdf',
]);
});
it('should skip external file deletion when deleted files have no URLs', async () => {
const service = createService();
Reflect.set(service, 'knowledgeBaseModel', {
deleteWithFiles: vi.fn().mockResolvedValue({
deletedFiles: [{ id: 'file-1', url: null }],
}),
});
await service.deleteKnowledgeBase('kb-1');
expect(deleteFilesSpy).not.toHaveBeenCalled();
});
});