feat(react-headless): expose token usage from openAIResponsesAdapter (#1078) - #1147
Open
justonemorenight wants to merge 1 commit into
Open
Conversation
…hesysdev#1078) Add `OpenAIResponsesAdapterOptions` with an optional `onUsage` callback to `openAIResponsesAdapter`. When the OpenAI Responses stream emits `response.completed`, if `event.response.usage` is present, call `options.onUsage` to report token usage to consumer applications. Also re-export `OpenAIResponsesAdapterOptions` from `@openuidev/react-headless` and add unit tests.
|
@justonemorenight is attempting to deploy a commit to the thesys-devs Team on Vercel. A member of the Team first needs to authorize it. |
justonemorenight
marked this pull request as ready for review
September 10, 2026 12:27
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Fixes #1078
Exposes an optional
onUsagecallback inopenAIResponsesAdapterso consuming applications can read token usage (prompt, completion, total tokens, and breakdown details) from the OpenAI Responses stream without having to maintain a custom adapter.Changes
OpenAIResponsesAdapterOptionsinterface withonUsage?: (usage: ResponseUsage) => void.openAIResponsesAdapter(options?: OpenAIResponsesAdapterOptions)to accept options.response.completedevent: whenevent.response?.usageis available, invokesoptions.onUsage(event.response.usage).OpenAIResponsesAdapterOptionsfrom@openuidev/react-headless.openai-responses.test.tsverifying:onUsageis invoked with the parsedResponseUsageonresponse.completed.options.Testing
pnpm --filter @openuidev/react-headless test— all 20 test files (190 tests) passed.