fix upload file size contract (#3408)

backend/app/gateway/routers/uploads.py

@@ -39,15 +39,39 @@ DEFAULT_MAX_FILE_SIZE = 50 * 1024 * 1024
 DEFAULT_MAX_TOTAL_SIZE = 100 * 1024 * 1024
 
 
+class UploadedFileInfo(BaseModel):
+    """Uploaded file metadata exposed by upload and list APIs."""
+
+    filename: str
+    size: int
+    path: str
+    virtual_path: str
+    artifact_url: str
+    extension: str | None = None
+    modified: float | None = None
+    original_filename: str | None = None
+    markdown_file: str | None = None
+    markdown_path: str | None = None
+    markdown_virtual_path: str | None = None
+    markdown_artifact_url: str | None = None
+
+
 class UploadResponse(BaseModel):
     """Response model for file upload."""
 
     success: bool
-    files: list[dict[str, str]]
+    files: list[UploadedFileInfo]
     message: str
     skipped_files: list[str] = Field(default_factory=list)
 
 
+class UploadListResponse(BaseModel):
+    """Response model for uploaded file listing."""
+
+    files: list[UploadedFileInfo]
+    count: int
+
+
 class UploadLimits(BaseModel):
     """Application-level upload limits exposed to clients."""
 
@@ -256,7 +280,7 @@ async def upload_files(
 
             file_info = {
                 "filename": safe_filename,
-                "size": str(file_size),
+                "size": file_size,
                 "path": str(sandbox_uploads / safe_filename),
                 "virtual_path": virtual_path,
                 "artifact_url": upload_artifact_url(thread_id, safe_filename),
@@ -333,9 +357,9 @@ async def get_upload_limits(
     return _get_upload_limits(config)
 
 
-@router.get("/list", response_model=dict)
+@router.get("/list", response_model=UploadListResponse)
 @require_permission("threads", "read", owner_check=True)
-async def list_uploaded_files(thread_id: str, request: Request) -> dict:
+async def list_uploaded_files(thread_id: str, request: Request) -> UploadListResponse:
     """List all files in a thread's uploads directory."""
     try:
         uploads_dir = get_uploads_dir(thread_id)
@@ -349,7 +373,7 @@ async def list_uploaded_files(thread_id: str, request: Request) -> dict:
     for f in result["files"]:
         f["path"] = str(sandbox_uploads / f["filename"])
 
-    return result
+    return UploadListResponse(**result)
 
 
 @router.delete("/{filename}")

backend/packages/harness/deerflow/client.py

@@ -1209,7 +1209,7 @@ class DeerFlowClient:
 
                 info: dict[str, Any] = {
                     "filename": dest_name,
-                    "size": str(dest.stat().st_size),
+                    "size": dest.stat().st_size,
                     "path": str(dest),
                     "virtual_path": upload_virtual_path(dest_name),
                     "artifact_url": upload_artifact_url(thread_id, dest_name),

backend/packages/harness/deerflow/uploads/manager.py

@@ -226,8 +226,7 @@ def list_files_in_dir(directory: Path) -> dict:
     Returns:
         Dict with "files" list (sorted by name) and "count".
         Each file entry has ``size`` as *int* (bytes).  Call
-        :func:`enrich_file_listing` to stringify sizes and add
-        virtual / artifact URLs.
+        :func:`enrich_file_listing` to add virtual / artifact URLs.
     """
     if not directory.is_dir():
         return {"files": [], "count": 0}
@@ -298,13 +297,12 @@ def upload_virtual_path(filename: str) -> str:
 
 
 def enrich_file_listing(result: dict, thread_id: str) -> dict:
-    """Add virtual paths, artifact URLs, and stringify sizes on a listing result.
+    """Add virtual paths and artifact URLs on a listing result.
 
     Mutates *result* in place and returns it for convenience.
     """
     for f in result["files"]:
         filename = f["filename"]
-        f["size"] = str(f["size"])
         f["virtual_path"] = upload_virtual_path(filename)
         f["artifact_url"] = upload_artifact_url(thread_id, filename)
     return result

backend/tests/test_client.py

@@ -1472,6 +1472,7 @@ class TestUploads:
             assert result["success"] is True
             assert len(result["files"]) == 1
             assert result["files"][0]["filename"] == "test.txt"
+            assert result["files"][0]["size"] == len("hello")
             assert "artifact_url" in result["files"][0]
             assert "message" in result
             assert (uploads_dir / "test.txt").exists()
@@ -1551,6 +1552,8 @@ class TestUploads:
             assert len(result["files"]) == 2
             names = {f["filename"] for f in result["files"]}
             assert names == {"a.txt", "b.txt"}
+            sizes = {f["filename"]: f["size"] for f in result["files"]}
+            assert sizes == {"a.txt": 1, "b.txt": 2}
             # Verify artifact_url is present
             for f in result["files"]:
                 assert "artifact_url" in f
@@ -2458,6 +2461,7 @@ class TestGatewayConformance:
         parsed = UploadResponse(**result)
         assert parsed.success is True
         assert len(parsed.files) == 1
+        assert parsed.files[0].size == len("hello")
 
     def test_get_memory_config(self, client):
         mem_cfg = MagicMock()

backend/tests/test_uploads_router.py

@@ -56,12 +56,40 @@ def test_upload_files_writes_thread_storage_and_skips_local_sandbox_sync(tmp_pat
 
     assert result.success is True
     assert len(result.files) == 1
-    assert result.files[0]["filename"] == "notes.txt"
+    assert result.files[0].filename == "notes.txt"
+    assert result.files[0].size == len(b"hello uploads")
     assert (thread_uploads_dir / "notes.txt").read_bytes() == b"hello uploads"
 
     sandbox.update_file.assert_not_called()
 
 
+def test_upload_and_list_response_models_expose_size_as_int(tmp_path):
+    thread_uploads_dir = tmp_path / "uploads"
+    thread_uploads_dir.mkdir(parents=True)
+    (thread_uploads_dir / "notes.txt").write_bytes(b"hello uploads")
+
+    paths = MagicMock()
+    paths.sandbox_uploads_dir.return_value = thread_uploads_dir
+
+    with (
+        patch.object(uploads, "get_uploads_dir", return_value=thread_uploads_dir),
+        patch.object(uploads, "get_paths", return_value=paths),
+    ):
+        result = asyncio.run(call_unwrapped(uploads.list_uploaded_files, "thread-local", request=MagicMock()))
+
+    assert result.count == 1
+    assert result.files[0].filename == "notes.txt"
+    assert result.files[0].size == len(b"hello uploads")
+
+
+def test_upload_openapi_schema_exposes_file_size_as_integer():
+    upload_schema = uploads.UploadResponse.model_json_schema()
+    list_schema = uploads.UploadListResponse.model_json_schema()
+
+    assert upload_schema["$defs"]["UploadedFileInfo"]["properties"]["size"]["type"] == "integer"
+    assert list_schema["$defs"]["UploadedFileInfo"]["properties"]["size"]["type"] == "integer"
+
+
 def test_upload_files_auto_renames_duplicate_form_filenames(tmp_path):
     thread_uploads_dir = tmp_path / "uploads"
     thread_uploads_dir.mkdir(parents=True)
@@ -88,9 +116,9 @@ def test_upload_files_auto_renames_duplicate_form_filenames(tmp_path):
         )
 
     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 [file_info.filename for file_info in result.files] == ["data.txt", "data_1.txt"]
+    assert result.files[0].original_filename is None
+    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"
 
@@ -138,8 +166,8 @@ def test_upload_files_does_not_auto_convert_documents_by_default(tmp_path):
 
     assert result.success is True
     assert len(result.files) == 1
-    assert result.files[0]["filename"] == "report.pdf"
-    assert "markdown_file" not in result.files[0]
+    assert result.files[0].filename == "report.pdf"
+    assert result.files[0].markdown_file is None
     convert_mock.assert_not_called()
     assert not (thread_uploads_dir / "report.md").exists()
 
@@ -172,8 +200,8 @@ def test_upload_files_syncs_non_local_sandbox_and_marks_markdown_file(tmp_path):
     assert result.success is True
     assert len(result.files) == 1
     file_info = result.files[0]
-    assert file_info["filename"] == "report.pdf"
-    assert file_info["markdown_file"] == "report.md"
+    assert file_info.filename == "report.pdf"
+    assert file_info.markdown_file == "report.md"
 
     assert (thread_uploads_dir / "report.pdf").read_bytes() == b"pdf-bytes"
     assert (thread_uploads_dir / "report.md").read_text(encoding="utf-8") == "converted"
@@ -516,7 +544,7 @@ def test_upload_files_rejects_dotdot_and_dot_filenames(tmp_path):
         result = asyncio.run(call_unwrapped(uploads.upload_files, "thread-local", request=MagicMock(), files=[file], config=SimpleNamespace()))
         assert result.success is True
         assert len(result.files) == 1
-        assert result.files[0]["filename"] == "passwd"
+        assert result.files[0].filename == "passwd"
 
     # Only the safely normalised file should exist
     assert [f.name for f in thread_uploads_dir.iterdir()] == ["passwd"]
@@ -616,7 +644,7 @@ def test_upload_files_overwrites_existing_regular_file(tmp_path):
         result = asyncio.run(uploads.upload_files("thread-local", files=[file]))
 
     assert result.success is True
-    assert [file_info["filename"] for file_info in result.files] == ["notes.txt"]
+    assert [file_info.filename for file_info in result.files] == ["notes.txt"]
     assert existing_file.read_bytes() == b"new upload"
     assert existing_file.stat().st_nlink == 1
 

frontend/src/core/uploads/api.ts

@@ -23,6 +23,7 @@ export interface UploadResponse {
   success: boolean;
   files: UploadedFileInfo[];
   message: string;
+  skipped_files: string[];
 }
 
 export interface ListFilesResponse {