NVIDIA / NVIDIA/nvcf

Support user/session affinity routing from the OpenAI user field

Open
#1,615 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Go
Stars
218
Forks
72
Avg merge
1d 12h
Merged PRs (30d)
427

Description

Is this related to a problem? Please describe.

OpenRouter sends a stable hashed end-user identifier in the top-level OpenAI request-body user field. NVCF currently cannot use this value for user- or session-affinity routing because it is not supplied as a routing header.

Describe the solution you'd like

Please support using the OpenAI user field as an input for user- or session-based routing on the NVCF LLM invocation path, so requests with the same identifier can be routed consistently.

Additional context

Example request sent by OpenRouter:

{
  "model": "nvidia/nvidia-nemotron-nano-9b-v2",
  "stream": true,
  "stream_options": {
    "include_usage": true
  },
  "user": "753fb7ba884d6cf36324110cb4e1beb8220887d3077384151c11a290f9308ec1",
  "messages": [
    {
      "role": "user",
      "content": "Hello from OpenRouter"
    }
  ]
}

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

The issue identifies the NVCF LLM invocation path but names no file or test. Start by locating parsing for the top-level OpenAI user field and the user/session-affinity routing logic, then trace how routing headers are supplied. Done means requests with the same identifier can use consistent user- or session-based routing, with relevant tests passing.

Written by the indexing model from the issue text.

Assessment

Tech stack
go
Domain
backend-api-design
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Active
Clarity
Mostly clear
Newbie friendliness
55/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.