From afb8b367ee537c58853c9b2c9a674728969f79eb Mon Sep 17 00:00:00 2001 From: "google-labs-jules[bot]" <161369871+google-labs-jules[bot]@users.noreply.github.com> Date: Sun, 17 May 2026 02:58:26 +0000 Subject: [PATCH 1/3] Fix SyntaxError caused by duplicate `event_hooks` in `httpx.AsyncClient` instantiation Combined duplicated `event_hooks` keyword arguments into a single dictionary parameter with both `validate_redirect` and `verify_redirect` in `app/api/url_upload.py`. This fixes a `SyntaxError: keyword argument repeated: event_hooks` and ensures that all redirect validations run. Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com> --- app/api/url_upload.py | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/app/api/url_upload.py b/app/api/url_upload.py index 1df8d020..9f20039c 100644 --- a/app/api/url_upload.py +++ b/app/api/url_upload.py @@ -194,11 +194,10 @@ async def process_url( async with httpx.AsyncClient( timeout=settings.http_request_timeout, follow_redirects=True, - event_hooks={"response": [validate_redirect]}, + event_hooks={"response": [validate_redirect, verify_redirect]}, headers={ "User-Agent": "DocuElevate/1.0", # Identify ourselves }, - event_hooks={"response": [verify_redirect]}, ) as client: async with client.stream("GET", url) as response: response.raise_for_status() From 18f5596b0149ffe44441e39f6d315fca16fe963a Mon Sep 17 00:00:00 2001 From: "google-labs-jules[bot]" <161369871+google-labs-jules[bot]@users.noreply.github.com> Date: Sun, 17 May 2026 03:01:11 +0000 Subject: [PATCH 2/3] Fix SyntaxError caused by duplicate `event_hooks` in `httpx.AsyncClient` instantiation Combined duplicated `event_hooks` keyword arguments into a single dictionary parameter with both `validate_redirect` and `verify_redirect` in `app/api/url_upload.py`. This fixes a `SyntaxError: keyword argument repeated: event_hooks` and ensures that all redirect validations run. Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com> From 871f788f0bd782ba8ad3a7d70e5cd4ccd24f749b Mon Sep 17 00:00:00 2001 From: Christian Krakau-Louis Date: Sun, 17 May 2026 13:12:55 +0200 Subject: [PATCH 3/3] fix(url-upload): handle unsafe redirects as client errors --- app/api/url_upload.py | 30 +++++++++++++----------------- tests/test_url_upload.py | 13 +++++++++++++ 2 files changed, 26 insertions(+), 17 deletions(-) diff --git a/app/api/url_upload.py b/app/api/url_upload.py index 9f20039c..b255407f 100644 --- a/app/api/url_upload.py +++ b/app/api/url_upload.py @@ -28,6 +28,10 @@ logger = logging.getLogger(__name__) router = APIRouter() +class UnsafeRedirectError(httpx.RequestError): + """Raised when a redirect target fails URL safety checks.""" + + class URLUploadRequest(BaseModel): """Request model for URL-based file upload""" @@ -120,9 +124,10 @@ async def verify_redirect(response: httpx.Response) -> None: try: validate_url_safety(new_url) except HTTPException as e: - # Map the validation error to an httpx exception so it can be handled - # properly by the caller, avoiding raw HTTPExceptions escaping the client scope - raise httpx.RequestError(f"Redirect to unsafe URL blocked: {e.detail}", request=response.request) from e + raise UnsafeRedirectError( + f"Redirect to unsafe URL blocked: {e.detail}", + request=response.request, + ) from e @router.post("/process-url") @@ -170,19 +175,6 @@ async def process_url( if not safe_filename: safe_filename = "download" - # Hook to validate redirects and prevent SSRF - async def validate_redirect(response: httpx.Response): - if response.is_redirect: - location = response.headers.get("Location") - if location: - # Resolve relative URLs - next_url = urllib.parse.urljoin(str(response.url), location) - try: - validate_url_safety(next_url) - except HTTPException as e: - # Reraise as a RequestError so httpx aborts the request - raise httpx.RequestError(f"Unsafe redirect target: {e.detail}", request=response.request) - # Download file with security measures # Initialize target_path to None to prevent UnboundLocalError in exception handlers # that may execute before target_path is assigned during error cases @@ -194,7 +186,7 @@ async def process_url( async with httpx.AsyncClient( timeout=settings.http_request_timeout, follow_redirects=True, - event_hooks={"response": [validate_redirect, verify_redirect]}, + event_hooks={"response": [verify_redirect]}, headers={ "User-Agent": "DocuElevate/1.0", # Identify ourselves }, @@ -284,6 +276,10 @@ async def process_url( logger.error(f"HTTP error while downloading file from URL: {url} - {str(e)}") raise HTTPException(status_code=e.response.status_code, detail=f"HTTP error: {str(e)}") + except UnsafeRedirectError as e: + logger.warning(f"Unsafe redirect blocked while downloading file from URL: {url} - {str(e)}") + raise HTTPException(status_code=400, detail=str(e)) + except httpx.RequestError as e: logger.error(f"Error downloading file from URL: {url} - {str(e)}") raise HTTPException(status_code=500, detail=f"Failed to download file: {str(e)}") diff --git a/tests/test_url_upload.py b/tests/test_url_upload.py index b3caaff8..0c83e440 100644 --- a/tests/test_url_upload.py +++ b/tests/test_url_upload.py @@ -465,6 +465,19 @@ class TestURLUploadEndpoint: data = response.json() assert "Failed to download file" in data["detail"] + @patch("app.api.url_upload.httpx.AsyncClient.stream") + def test_process_url_unsafe_redirect_returns_400(self, mock_stream, client): + """Test unsafe redirects are reported as a client error instead of HTTP 500.""" + from app.api.url_upload import UnsafeRedirectError + + mock_stream.side_effect = UnsafeRedirectError("Redirect to unsafe URL blocked: Unsafe URL") + + response = client.post("/api/process-url", json={"url": "https://example.com/file.pdf"}) + + assert response.status_code == 400 + data = response.json() + assert "Redirect to unsafe URL blocked" in data["detail"] + @patch("app.api.url_upload.httpx.AsyncClient.stream") def test_process_url_oserror_during_save(self, mock_stream, client, tmp_path, monkeypatch): """Test handling of OSError when saving file"""