fix(server): frequent embedding (#13475)

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

- New Features
- Smarter embedding pipeline skips re-embedding when content hasn’t
changed; added content sanitization for embeddings and workspace content
retrieval.
- Bug Fixes
- Re-embedding now requires both a document update and the last
embedding being older than 10 minutes, reducing unnecessary work.
- Refactor
- Consolidated embedding preprocessing and moved sanitization utilities
into shared models; upserts now refresh stored content.
- Tests
- Expanded snapshot-based tests covering multiple time/age scenarios for
embedding decision logic.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->

packages/backend/server/src/plugins/copilot/tools/doc-semantic-search.ts

@@ -3,11 +3,14 @@ import { omit } from 'lodash-es';
 import { z } from 'zod';
 
 import type { AccessController } from '../../../core/permission';
-import type { ChunkSimilarity, Models } from '../../../models';
+import {
+  type ChunkSimilarity,
+  clearEmbeddingChunk,
+  type Models,
+} from '../../../models';
 import type { CopilotContextService } from '../context';
 import type { ContextSession } from '../context/session';
 import type { CopilotChatOptions } from '../providers';
-import { clearEmbeddingChunk } from '../utils';
 import { toolError } from './error';
 
 export const buildDocSearchGetter = (