Skip to content

Conversation

@ygree
Copy link
Contributor

@ygree ygree commented Nov 13, 2025

What Does This Do

Adds openai-java v3.0+ instrumentation for completions, chat completions, embeddings, and responses.

image
image

Motivation

Additional Notes

Contributor Checklist

Jira ticket: AIDM-163

ygree added 30 commits October 24, 2025 18:03
…d "streamed async request completion test with withRawResponse"
Call decorateWithResponse from the wrappers
Rename span resources to be aligned with trace-py
Add http.client resource assertion
Test case renaming
Reorder tests by synch, async
Fix Embeddings fixture for the latestDepTest when base64
Copy link

@chatgpt-codex-connector chatgpt-codex-connector bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 21025e87d0

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

Copy link
Contributor

@amarziali amarziali left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I don't know the API in depth but the instrumentation looks ok from my standpoint.

Copy link
Member

@Kyle-Verhoog Kyle-Verhoog left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

great stuff yury 👏

just found one major inconsistency with the tag prefix which i think might be responsible for a bunch of the behaviour we were seeing in the bugbash

@ygree
Copy link
Contributor Author

ygree commented Jan 30, 2026

great stuff yury 👏

just found one major inconsistency with the tag prefix which i think might be responsible for a bunch of the behaviour we were seeing in the bugbash

Thanks, Kyle! The tag prefix is stripped by the LLMObsSpanMapper, which doesn't affect the cost calculation. I think the prefix was introduced to scope and hide LLMObs-specific data when passed via span tags. This didn't change with this PR.

@ygree
Copy link
Contributor Author

ygree commented Jan 31, 2026

/merge

@gh-worker-devflow-routing-ef8351
Copy link

gh-worker-devflow-routing-ef8351 bot commented Jan 31, 2026

View all feedbacks in Devflow UI.

2026-01-31 06:18:32 UTC ℹ️ Start processing command /merge


2026-01-31 06:18:37 UTC ℹ️ MergeQueue: pull request added to the queue

The expected merge time in master is approximately 0s (p90).


2026-01-31 07:12:25 UTC ℹ️ MergeQueue: This merge request was merged

@gh-worker-dd-mergequeue-cf854d gh-worker-dd-mergequeue-cf854d bot merged commit 0253f31 into master Jan 31, 2026
551 of 554 checks passed
@gh-worker-dd-mergequeue-cf854d gh-worker-dd-mergequeue-cf854d bot deleted the ygree/openai-java branch January 31, 2026 07:12
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

comp: mlobs ML Observability (LLMObs) inst: others All other instrumentations mergequeue-status: done type: feature request

Projects

None yet

Development

Successfully merging this pull request may close these issues.

7 participants