Fix duplicate gateway upload filenames (#2789)

backend/CLAUDE.md

@@ -520,6 +520,7 @@ Multi-file upload with automatic document conversion:
 - Rejects directory inputs before copying so uploads stay all-or-nothing
 - Reuses one conversion worker per request when called from an active event loop
 - Files stored in thread-isolated directories
+- Duplicate filenames in a single upload request are auto-renamed with `_N` suffixes so later files do not truncate earlier files
 - Agent receives uploaded file list via `UploadsMiddleware`
 
 See [docs/FILE_UPLOAD.md](docs/FILE_UPLOAD.md) for details.

backend/README.md

@@ -124,7 +124,7 @@ FastAPI application providing REST endpoints for frontend integration:
 | `POST /api/memory/reload` | Force memory reload |
 | `GET /api/memory/config` | Memory configuration |
 | `GET /api/memory/status` | Combined config + data |
-| `POST /api/threads/{id}/uploads` | Upload files (auto-converts PDF/PPT/Excel/Word to Markdown, rejects directory paths) |
+| `POST /api/threads/{id}/uploads` | Upload files (auto-converts PDF/PPT/Excel/Word to Markdown, rejects directory paths, auto-renames duplicate filenames in one request) |
 | `GET /api/threads/{id}/uploads/list` | List uploaded files |
 | `DELETE /api/threads/{id}` | Delete DeerFlow-managed local thread data after LangGraph thread deletion; unexpected failures are logged server-side and return a generic 500 detail |
 | `GET /api/threads/{id}/artifacts/{path}` | Serve generated artifacts |

backend/app/gateway/routers/uploads.py

@@ -16,6 +16,7 @@ from deerflow.sandbox.sandbox_provider import SandboxProvider, get_sandbox_provi
 from deerflow.uploads.manager import (
     PathTraversalError,
     UnsafeUploadPathError,
+    claim_unique_filename,
     delete_file_safe,
     enrich_file_listing,
     ensure_uploads_dir,
@@ -192,6 +193,10 @@ async def upload_files(
     sandbox_sync_targets = []
     skipped_files = []
     total_size = 0
+    # Track filenames within this request so duplicate form parts do not
+    # silently truncate each other. Existing uploads keep the historical
+    # overwrite behavior for a single replacement upload.
+    seen_filenames: set[str] = set()
 
     sandbox_provider = get_sandbox_provider()
     sync_to_sandbox = not _uses_thread_data_mounts(sandbox_provider)
@@ -208,7 +213,8 @@ async def upload_files(
             continue
 
         try:
-            safe_filename = normalize_filename(file.filename)
+            original_filename = normalize_filename(file.filename)
+            safe_filename = claim_unique_filename(original_filename, seen_filenames)
         except ValueError:
             logger.warning(f"Skipping file with unsafe filename: {file.filename!r}")
             continue
@@ -236,6 +242,8 @@ async def upload_files(
                 "virtual_path": virtual_path,
                 "artifact_url": upload_artifact_url(thread_id, safe_filename),
             }
+            if safe_filename != original_filename:
+                file_info["original_filename"] = original_filename
 
             logger.info(f"Saved file: {safe_filename} ({file_size} bytes) to {file_info['path']}")
 

backend/tests/test_uploads_router.py

@@ -61,6 +61,39 @@ def test_upload_files_writes_thread_storage_and_skips_local_sandbox_sync(tmp_pat
     sandbox.update_file.assert_not_called()
 
 
+def test_upload_files_auto_renames_duplicate_form_filenames(tmp_path):
+    thread_uploads_dir = tmp_path / "uploads"
+    thread_uploads_dir.mkdir(parents=True)
+
+    provider = MagicMock()
+    provider.uses_thread_data_mounts = True
+
+    with (
+        patch.object(uploads, "get_uploads_dir", return_value=thread_uploads_dir),
+        patch.object(uploads, "ensure_uploads_dir", return_value=thread_uploads_dir),
+        patch.object(uploads, "get_sandbox_provider", return_value=provider),
+    ):
+        result = asyncio.run(
+            call_unwrapped(
+                uploads.upload_files,
+                "thread-local",
+                request=MagicMock(),
+                files=[
+                    UploadFile(filename="data.txt", file=BytesIO(b"first")),
+                    UploadFile(filename="data.txt", file=BytesIO(b"second")),
+                ],
+                config=SimpleNamespace(),
+            )
+        )
+
+    assert result.success is True
+    assert [file_info["filename"] for file_info in result.files] == ["data.txt", "data_1.txt"]
+    assert "original_filename" not in result.files[0]
+    assert result.files[1]["original_filename"] == "data.txt"
+    assert (thread_uploads_dir / "data.txt").read_bytes() == b"first"
+    assert (thread_uploads_dir / "data_1.txt").read_bytes() == b"second"
+
+
 def test_upload_files_skips_acquire_when_thread_data_is_mounted(tmp_path):
     thread_uploads_dir = tmp_path / "uploads"
     thread_uploads_dir.mkdir(parents=True)