feat(server): attachment embedding (#13348)

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

* **New Features**
* Added support for managing "blobs" in Copilot context, including
adding and removing blobs via new GraphQL mutations and UI fields.
* Introduced tracking and querying of blob embeddings within workspaces,
enabling search and similarity matching for blob content.
* Extended Copilot context and workspace APIs, schema, and UI to display
and manage blobs alongside existing documents and files.

* **Bug Fixes**
* Updated context and embedding status logic to handle blobs, ensuring
accurate status reporting and embedding management.

* **Tests**
* Added and updated test cases and snapshots to cover blob embedding
insertion, matching, and removal scenarios.

* **Documentation**
* Updated GraphQL schema and TypeScript types to reflect new
blob-related fields and mutations.

* **Chores**
* Refactored and cleaned up code to support new blob entity and
embedding logic, including renaming and updating internal methods and
types.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->

packages/backend/server/src/__tests__/copilot.spec.ts

@@ -1520,14 +1520,17 @@ test('TextStreamParser should process a sequence of message chunks', t => {
 
 // ==================== context ====================
 test('should be able to manage context', async t => {
-  const { context, prompt, session, event, jobs, storage } = t.context;
+  const { context, db, event, jobs, prompt, session, storage, workspace } =
+    t.context;
+
+  const ws = await workspace.create(userId);
 
   await prompt.set(promptName, 'model', [
     { role: 'system', content: 'hello {{word}}' },
   ]);
   const chatSession = await session.create({
     docId: 'test',
-    workspaceId: 'test',
+    workspaceId: ws.id,
     userId,
     promptName,
     pinned: false,
@@ -1608,6 +1611,36 @@ test('should be able to manage context', async t => {
       t.is(result[0].fileId, file.id, 'should match file id');
     }
 
+    // blob record
+    {
+      const blobId = 'test-blob';
+      await storage.put(userId, session.workspaceId, blobId, buffer);
+      await db.blob.create({
+        data: {
+          workspaceId: session.workspaceId,
+          key: blobId,
+          size: buffer.length,
+          mime: 'application/pdf',
+        },
+      });
+
+      await jobs.embedPendingBlob({
+        userId,
+        workspaceId: session.workspaceId,
+        blobId,
+      });
+
+      const result = await t.context.context.matchWorkspaceBlobs(
+        session.workspaceId,
+        'test',
+        1,
+        undefined,
+        1
+      );
+      t.is(result.length, 1, 'should match blob embedding');
+      t.is(result[0].blobId, blobId, 'should match blob id');
+    }
+
     // doc record
 
     const addDoc = async () => {

packages/backend/server/src/__tests__/models/__snapshots__/copilot-workspace.spec.ts.md

@@ -74,6 +74,17 @@ Generated by [AVA](https://avajs.dev).
       },
     ]
 
+> should match workspace blob embedding
+
+    [
+      {
+        blobId: 'blob-test',
+        chunk: 0,
+        content: 'blob content',
+        distance: 0,
+      },
+    ]
+
 > should find docs to embed
 
     1

packages/backend/server/src/__tests__/models/copilot-context.spec.ts

@@ -89,13 +89,14 @@ test('should get null for non-exist job', async t => {
 
 test('should update context', async t => {
   const { id: contextId } = await t.context.copilotContext.create(sessionId);
-  const config = await t.context.copilotContext.getConfig(contextId);
+  const config = (await t.context.copilotContext.getConfig(contextId))!;
+  t.assert(config, 'should get context config');
 
   const doc = {
     id: docId,
     createdAt: Date.now(),
   };
-  config?.docs.push(doc);
+  config.docs.push(doc);
   await t.context.copilotContext.update(contextId, { config });
 
   const config1 = await t.context.copilotContext.getConfig(contextId);
@@ -164,7 +165,7 @@ test('should insert embedding by doc id', async t => {
     );
 
     {
-      const ret = await t.context.copilotContext.listWorkspaceEmbedding(
+      const ret = await t.context.copilotContext.listWorkspaceDocEmbedding(
         workspace.id,
         [docId]
       );
@@ -320,7 +321,7 @@ test('should merge doc status correctly', async t => {
 
     const hasEmbeddingStub = Sinon.stub(
       t.context.copilotContext,
-      'listWorkspaceEmbedding'
+      'listWorkspaceDocEmbedding'
     ).resolves([]);
 
     const stubResult = await t.context.copilotContext.mergeDocStatus(

packages/backend/server/src/__tests__/models/copilot-workspace.spec.ts

@@ -145,6 +145,52 @@ test('should insert and search embedding', async t => {
     }
   }
 
+  {
+    await t.context.db.blob.create({
+      data: {
+        workspaceId: workspace.id,
+        key: 'blob-test',
+        mime: 'text/plain',
+        size: 1,
+      },
+    });
+
+    const blobId = 'blob-test';
+    await t.context.copilotWorkspace.insertBlobEmbeddings(
+      workspace.id,
+      blobId,
+      [
+        {
+          index: 0,
+          content: 'blob content',
+          embedding: Array.from({ length: 1024 }, () => 1),
+        },
+      ]
+    );
+
+    {
+      const ret = await t.context.copilotWorkspace.matchBlobEmbedding(
+        workspace.id,
+        Array.from({ length: 1024 }, () => 0.9),
+        1,
+        1
+      );
+      t.snapshot(cleanObject(ret), 'should match workspace blob embedding');
+    }
+
+    await t.context.copilotWorkspace.removeBlob(workspace.id, blobId);
+
+    {
+      const ret = await t.context.copilotWorkspace.matchBlobEmbedding(
+        workspace.id,
+        Array.from({ length: 1024 }, () => 0.9),
+        1,
+        1
+      );
+      t.deepEqual(ret, [], 'should not match after removal');
+    }
+  }
+
   {
     const docId = randomUUID();
     await t.context.doc.upsert({

packages/backend/server/src/__tests__/utils/copilot.ts

@@ -369,7 +369,6 @@ export async function listContextDocAndFiles(
                 docs {
                   id
                   status
-                  error
                   createdAt
                 }
                 files {