diff --git a/backend/package/yuxi/plugins/parser/unified.py b/backend/package/yuxi/plugins/parser/unified.py
index 7e263256..77cbf488 100644
--- a/backend/package/yuxi/plugins/parser/unified.py
+++ b/backend/package/yuxi/plugins/parser/unified.py
@@ -127,31 +127,25 @@ def _convert_with_docling(file_path: Path, params: dict | None = None) -> str:
     doc = result.document
 
     if hasattr(doc, "pictures") and doc.pictures:
-        image_refs: list[tuple[str, bytes]] = []
-
+        replacements: list[str] = []
         for pic in doc.pictures:
-            if hasattr(pic, "image") and hasattr(pic.image, "uri"):
-                uri = str(pic.image.uri)
-                if uri.startswith("data:"):
+            uri = str(pic.image.uri) if hasattr(pic, "image") and hasattr(pic.image, "uri") else ""
+            if uri.startswith("data:"):
+                filename = "image"
+                try:
                     image_data, mime_type = _parse_data_uri(uri)
-                    timestamp = int(time.time() * 1000000)
-                    filename = f"image_{timestamp}.{mime_type.split('/')[-1]}"
-                    image_refs.append((filename, image_data))
-
-        image_urls: list[str] = []
-        for filename, image_data in image_refs:
-            try:
-                url = _upload_image_to_minio(image_data, filename, image_bucket, image_prefix)
-                image_urls.append(f"![{filename}]({url})")
-            except Exception as e:  # noqa: BLE001
-                logger.error(f"上传图片失败 {filename}: {e}")
-                image_urls.append(f"[图片: {filename}]")
+                    filename = f"image_{int(time.time() * 1000000)}.{mime_type.split('/')[-1]}"
+                    url = _upload_image_to_minio(image_data, filename, image_bucket, image_prefix)
+                    replacements.append(f"![{filename}]({url})")
+                except Exception as e:  # noqa: BLE001
+                    logger.error(f"上传图片失败 {filename}: {e}")
+                    replacements.append(f"[图片: {filename}]")
+            else:
+                replacements.append("")
 
         markdown = doc.export_to_markdown()
-
-        for url in image_urls:
-            markdown = re.sub(r"<!--\s*image\s*-->", url, markdown, count=1)
-
+        for replacement in replacements:
+            markdown = re.sub(r"<!--\s*image\s*-->", replacement, markdown, count=1)
         return markdown
 
     return doc.export_to_markdown()
diff --git a/backend/test/unit/plugins/test_parser_facade.py b/backend/test/unit/plugins/test_parser_facade.py
index 21857308..e3d1d4ce 100644
--- a/backend/test/unit/plugins/test_parser_facade.py
+++ b/backend/test/unit/plugins/test_parser_facade.py
@@ -76,9 +76,10 @@ def test_convert_with_docling_reinserts_image_links_in_document_order(
     fake_doc = SimpleNamespace(
         pictures=[
             SimpleNamespace(image=SimpleNamespace(uri=f"data:image/png;base64,{first_image}")),
+            SimpleNamespace(image=SimpleNamespace(uri="https://example.test/remote.png")),
             SimpleNamespace(image=SimpleNamespace(uri=f"data:image/png;base64,{second_image}")),
         ],
-        export_to_markdown=lambda: "before\n<!-- image -->\nbetween\n<!-- image -->\nafter",
+        export_to_markdown=lambda: "before\n<!-- image -->\nremote\n<!-- image -->\nbetween\n<!-- image -->\nafter",
     )
     fake_result = SimpleNamespace(status=SimpleNamespace(name="SUCCESS"), document=fake_doc)
     uploaded_images: list[bytes] = []
@@ -103,12 +104,44 @@ def test_convert_with_docling_reinserts_image_links_in_document_order(
     assert markdown == (
         "before\n"
         "![image_1000000.png](https://example.test/1.png)\n"
+        "remote\n"
+        "\n"
         "between\n"
         "![image_2000000.png](https://example.test/2.png)\n"
         "after"
     )
 
 
+def test_convert_with_docling_keeps_image_placeholder_when_upload_fails(
+    tmp_path: Path,
+    monkeypatch: pytest.MonkeyPatch,
+):
+    file_path = tmp_path / "parser_test.docx"
+    file_path.write_bytes(b"fake docx")
+    image = base64.b64encode(b"image data").decode()
+    fake_doc = SimpleNamespace(
+        pictures=[SimpleNamespace(image=SimpleNamespace(uri=f"data:image/png;base64,{image}"))],
+        export_to_markdown=lambda: "before\n<!-- image -->\nafter",
+    )
+    fake_result = SimpleNamespace(status=SimpleNamespace(name="SUCCESS"), document=fake_doc)
+
+    class FakeConverter:
+        def convert(self, path: Path):
+            assert path == file_path
+            return fake_result
+
+    def _raise_upload_error(*args, **kwargs):
+        raise RuntimeError("upload failed")
+
+    monkeypatch.setattr(parser_unified, "_get_docling_converter", lambda: FakeConverter())
+    monkeypatch.setattr(parser_unified, "_upload_image_to_minio", _raise_upload_error)
+    monkeypatch.setattr(parser_unified.time, "time", lambda: 1.0)
+
+    markdown = parser_unified._convert_with_docling(file_path)
+
+    assert markdown == "before\n[图片: image_1000000.png]\nafter"
+
+
 def test_parser_parse_png_file_returns_markdown_text_with_mocked_ocr(
     tmp_path: Path,
     monkeypatch: pytest.MonkeyPatch,