Skip to content

Conversation

@LucasSugi
Copy link
Contributor

Title

feat: Add headers to VLLM Passthrough requests [Log success Events]

Relevant issues

Pre-Submission checklist

Please complete all items before asking a LiteLLM maintainer to review your PR

  • I have Added testing in the tests/litellm/ directory, Adding at least 1 test is a hard requirement - see details
  • I have added a screenshot of my new test passing locally
  • My PR passes all unit tests on make test-unit
  • My PR's scope is as isolated as possible, it only solves 1 specific problem

Type

🆕 New Feature
🐛 Bug Fix

Changes

I set a breakpoint inside the async_log_success_event function for a CustomLogger. You can check that in kwargs -> litellm_params -> proxy_server_request the headers do not exist.
Screenshot 2025-11-12 at 10 33 02

Here it's after the modifcation, add the header to be retrieve for callback function
Screenshot 2025-11-12 at 10 34 16

Unit test for the function I make changes
Screenshot 2025-11-12 at 10 50 52

Just to concern, you can check the headers I am adding does not have relation to the headers retrieved in the request for client. The x-requester-token for example that appears in the other print is not shown here.
Screenshot 2025-11-12 at 10 54 06

@vercel
Copy link

vercel bot commented Nov 12, 2025

@LucasSugi is attempting to deploy a commit to the CLERKIEAI Team on Vercel.

A member of the Team first needs to authorize it.

@krrishdholakia krrishdholakia merged commit e1c607e into BerriAI:main Nov 13, 2025
3 of 6 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants