feat(ai-gateway): log Vercel upstream provider id as upstream_id - #4828
Merged
Conversation
The Vercel AI Gateway reports the upstream provider's own request/response id in provider_metadata.gateway.routing.modelAttempts[].providerAttempts[]. Until now upstream_id was only populated from an OpenRouter-style /generation lookup, which is skipped for healthy Vercel requests, so microdollar_usage_metadata never recorded it. Extract it in all chat_completions, messages and responses parse paths, using the same serving-attempt selection as the BYOK extraction.
Contributor
Code Review SummaryStatus: No Issues Found | Recommendation: Merge Executive SummaryReviewed the Vercel AI Gateway Files Reviewed (9 files)
Reviewed by claude-sonnet-5 · Input: 20 · Output: 4.8K · Cached: 413.9K Review guidance: REVIEW.md from base branch |
lambertjosh
approved these changes
Jul 28, 2026
marius-kilocode
approved these changes
Jul 28, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem
The Vercel AI Gateway reports the upstream provider's own id in
provider_metadata.gateway.routing.modelAttempts[].providerAttempts[].providerRequestId(and
providerResponseId), e.g. Fireworks'chatcmpl-ccebc94c526d4f8797cfe00023478a9a.microdollar_usage_metadata.upstream_idwas only ever populated from theOpenRouter-style
GET /generation?id=…lookup, and that lookup is skipped forhealthy Vercel requests (they already report cost and
finalProvider), so theupstream provider id was never logged.
Change
VercelProviderAttemptnow modelsproviderRequestId/providerResponseId.extractVercelUpstreamId()inprocessUsage.shared.ts, sharing theserving-attempt selection with
extractVercelIsByok()viafindVercelServingProviderAttempt().upstream_id: null: chat_completions (stream + JSON), messages (stream +JSON), responses (stream + JSON).
processTokenDatano longer clobbers a response-derivedupstream_idwith anull from the
/generationmerge.Verification
jest src/lib/ai-gateway/processUsage— 74 passed, including three newchat_completions tests (streamed id, missing id stays null, non-streamed id).
vercel-messages/vercel-responsesapproval fixtures already containedproviderRequestId; their approved output now shows the real upstream idsinstead of
null.tsgo --noEmit,pnpm lint,pnpm format.