feat(server): cleanup trashed doc's embedding (#13201)

fix AI-359

<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit

* **New Features**
* Added automated cleanup of embeddings for documents deleted or trashed
from workspaces.
* Introduced a new job to schedule and perform this cleanup per
workspace daily and on demand.
  * Added new GraphQL mutation to manually trigger the cleanup process.
* Added the ability to list workspaces with flexible filtering and
selection options.

* **Improvements**
* Enhanced document status handling to more accurately reflect embedding
presence.
* Refined internal methods for managing and checking document
embeddings.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
This commit is contained in:
DarkSky
2025-07-15 20:00:33 +08:00
committed by GitHub
parent a4b535a42a
commit cc1d5b497a
12 changed files with 148 additions and 22 deletions
@@ -164,11 +164,14 @@ test('should insert embedding by doc id', async t => {
);
{
const ret = await t.context.copilotContext.hasWorkspaceEmbedding(
const ret = await t.context.copilotContext.listWorkspaceEmbedding(
workspace.id,
[docId]
);
t.true(ret.has(docId), 'should return doc id when embedding is inserted');
t.true(
ret.includes(docId),
'should return doc id when embedding is inserted'
);
}
{
@@ -317,8 +320,8 @@ test('should merge doc status correctly', async t => {
const hasEmbeddingStub = Sinon.stub(
t.context.copilotContext,
'hasWorkspaceEmbedding'
).resolves(new Set<string>());
'listWorkspaceEmbedding'
).resolves([]);
const stubResult = await t.context.copilotContext.mergeDocStatus(
workspace.id,