Conversation
PAIR's inference proxy endpoints are intended for native clients, but the shared wildcard CORS policy allowed browser origins to send requests and read proxy or engine responses. This removes that and updates tests and documentation to match. Signed-off-by: Kaylee Lubick <klubick@nvidia.com>
Collaborator
Author
|
Internal tests pass: https://gitlab-master.nvidia.com/dhc/personal-ai-router/-/pipelines/67784955 |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description
PAIR's inference proxy endpoints are intended for native clients, but the shared wildcard CORS policy allowed browser origins to send requests and read proxy or engine responses.
This removes that and updates tests and documentation to match.
This bumps
ollama-proxyandlmstudio-proxybecause of the new behavior.Scope
Blocking browser-based queries on our proxies is only layer in a defense-in-depth strategy. See SECURITY.md for more
Validation
I ran tests locally and spun up a local 1-node instance to do inference to make sure one CUJ works.
Risk
There might be other CUJs I'm not familiar with that will break. If they do, we'll want to be more careful than just a wildcard Allow.
Checklist
git commit -s), certifying the Developer Certificate of Origin.services/versions.json, and described user-visible changes above so they reach the release notes.