feat: add .docx upload support with text extraction

- Add DOCX MIME type to ALLOWED_DOCUMENT_TYPES in storage_service.py
- Add python-docx text extraction in _generate_ai_description
- Extract shared _store_document_content helper for PDF/DOCX
- Add python-docx>=1.1.0 to requirements.txt
- Add tests for docx upload acceptance and document fetch

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

backend/tests/test_uploads.py

@@ -158,6 +158,31 @@ async def test_upload_accepts_pdf(client, auth_headers):
     assert data["content_type"] == "application/pdf"
 
 
+@pytest.mark.asyncio
+async def test_upload_accepts_docx(client, auth_headers):
+    """Upload accepts .docx files."""
+    fake_key = f"uploads/acc/{uuid.uuid4()}.docx"
+    fake_url = "https://fake-s3.example.com/presigned?token=docx"
+    docx_mime = "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
+
+    with patch("app.api.endpoints.uploads.settings") as mock_settings, \
+         patch("app.api.endpoints.uploads.storage_service") as mock_storage:
+        mock_settings.STORAGE_ENDPOINT = "http://fake-s3"
+        mock_storage.validate_upload.return_value = None
+        mock_storage.MAX_FILES_PER_SESSION = 20
+        mock_storage.MAX_BYTES_PER_SESSION = 50 * 1024 * 1024
+        mock_storage.upload_file = AsyncMock(return_value=fake_key)
+        mock_storage.get_presigned_url.return_value = fake_url
+
+        files = {"file": ("runbook.docx", io.BytesIO(b"PK\x03\x04 fake docx"), docx_mime)}
+        response = await client.post("/api/v1/uploads", files=files, headers=auth_headers)
+
+    assert response.status_code == 201
+    data = response.json()
+    assert data["filename"] == "runbook.docx"
+    assert data["content_type"] == docx_mime
+
+
 @pytest.mark.asyncio
 async def test_upload_rejects_oversized_pdf(client, auth_headers):
     """Upload rejects PDF files exceeding 10 MB."""
@@ -464,6 +489,40 @@ async def test_fetch_upload_documents_respects_account_filter(client, auth_heade
     assert len(docs) == 0
 
 
+@pytest.mark.asyncio
+async def test_fetch_upload_documents_returns_docx_content(client, auth_headers, test_db):
+    """fetch_upload_documents returns extracted_content for DOCX uploads."""
+    from app.models.file_upload import FileUpload
+    from app.models.user import User
+    from app.services.storage_service import fetch_upload_documents
+    from sqlalchemy import select
+
+    result = await test_db.execute(select(User).where(User.email == "test@example.com"))
+    user = result.scalar_one()
+
+    docx_mime = "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
+    upload = FileUpload(
+        account_id=user.account_id,
+        uploaded_by=user.id,
+        session_id=None,
+        filename="runbook.docx",
+        content_type=docx_mime,
+        size_bytes=8000,
+        storage_key=f"uploads/{user.account_id}/{uuid.uuid4()}.docx",
+        extracted_content="Step 1: Restart the service\n\nStep 2: Verify logs",
+    )
+    test_db.add(upload)
+    await test_db.commit()
+    await test_db.refresh(upload)
+
+    docs = await fetch_upload_documents([upload.id], user.account_id, test_db)
+
+    assert len(docs) == 1
+    assert docs[0]["filename"] == "runbook.docx"
+    assert docs[0]["content_type"] == docx_mime
+    assert "Restart the service" in docs[0]["text"]
+
+
 @pytest.mark.asyncio
 async def test_fetch_upload_documents_empty_ids(client, auth_headers, test_db):
     """Empty upload_ids returns empty list without querying DB."""