NVIDIA / NVIDIA/Personal-AI-Router
[Feature]: The return needs to include the node that was used to complete the request in order for it to be logged.
Nobody has claimed this yet.
- Dominant language
- Go
- Stars
- 1.4k
- Forks
- 250
- Avg merge
- 23h 27m
- Merged PRs (30d)
- 1
Description
Area
Desktop experience
User problem
In most cases you will want to log the [Prompt Tokens], [Completion Tokens], [Total Tokens],[Tokens per Second], [SystemPrompt], [UserPrompt],[Response],[Endpoint].
Desired outcome
In most cases you will want to log the [Prompt Tokens], [Completion Tokens], [Total Tokens],[Tokens per Second], [SystemPrompt], [UserPrompt],[Response],[Endpoint].
Alternatives considered
A method to tie Nvidia Pair to log all calls including which node was used for Prompt logging.
Compatibility and security implications
No response
Validation approach
No response
Confirmations
- I searched existing issues for duplicates.
- I agree to follow the Code of Conduct.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
No file, test, or entry point is named. Start by tracing how requests are completed and how the selected node is represented in the return value; clarify the expected response shape and logging path with maintainers. Done means the node used for a request is available to callers for logging without breaking existing consumers.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- go
- Domain
- desktop
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Active
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100