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 -->

packages/backend/server/src/plugins/copilot/embedding/job.ts

@@ -12,6 +12,7 @@ import {
   OnJob,
 } from '../../../base';
 import { DocReader } from '../../../core/doc';
+import { readAllDocIdsFromWorkspaceSnapshot } from '../../../core/utils/blocksuite';
 import { Models } from '../../../models';
 import { CopilotStorage } from '../storage';
 import { readStream } from '../utils';
@@ -134,10 +135,30 @@ export class CopilotEmbeddingJob {
     if (enableDocEmbedding) {
       const toBeEmbedDocIds =
         await this.models.copilotWorkspace.findDocsToEmbed(workspaceId);
+      if (!toBeEmbedDocIds.length) {
+        return;
+      }
+      // filter out trashed docs
+      const rootSnapshot = await this.models.doc.getSnapshot(
+        workspaceId,
+        workspaceId
+      );
+      if (!rootSnapshot) {
+        this.logger.warn(
+          `Root snapshot for workspace ${workspaceId} not found, skipping embedding.`
+        );
+        return;
+      }
+      const allDocIds = new Set(
+        readAllDocIdsFromWorkspaceSnapshot(rootSnapshot.blob)
+      );
       this.logger.log(
         `Trigger embedding for ${toBeEmbedDocIds.length} docs in workspace ${workspaceId}`
       );
-      for (const docId of toBeEmbedDocIds) {
+      const finalToBeEmbedDocIds = toBeEmbedDocIds.filter(docId =>
+        allDocIds.has(docId)
+      );
+      for (const docId of finalToBeEmbedDocIds) {
         await this.queue.add(
           'copilot.embedding.docs',
           {
@@ -422,4 +443,39 @@ export class CopilotEmbeddingJob {
       );
     }
   }
+
+  @OnJob('copilot.embedding.cleanupTrashedDocEmbeddings')
+  async cleanupTrashedDocEmbeddings({
+    workspaceId,
+  }: Jobs['copilot.embedding.cleanupTrashedDocEmbeddings']) {
+    const workspace = await this.models.workspace.get(workspaceId);
+    if (!workspace) {
+      this.logger.warn(`workspace ${workspaceId} not found`);
+      return;
+    }
+
+    const snapshot = await this.models.doc.getSnapshot(
+      workspaceId,
+      workspaceId
+    );
+    if (!snapshot) {
+      this.logger.warn(`workspace snapshot ${workspaceId} not found`);
+      return;
+    }
+
+    const docIdsInWorkspace = readAllDocIdsFromWorkspaceSnapshot(snapshot.blob);
+    const docIdsInEmbedding =
+      await this.models.copilotContext.listWorkspaceEmbedding(workspaceId);
+    const docIdsInWorkspaceSet = new Set(docIdsInWorkspace);
+
+    const deletedDocIds = docIdsInEmbedding.filter(
+      docId => !docIdsInWorkspaceSet.has(docId)
+    );
+    for (const docId of deletedDocIds) {
+      await this.models.copilotContext.deleteWorkspaceEmbedding(
+        workspaceId,
+        docId
+      );
+    }
+  }
 }

packages/backend/server/src/plugins/copilot/embedding/types.ts

@@ -61,6 +61,10 @@ declare global {
       fileId: string;
       fileName: string;
     };
+
+    'copilot.embedding.cleanupTrashedDocEmbeddings': {
+      workspaceId: string;
+    };
   }
 }