fix(tracing): Align cache token attributes with Sentry conventions#403
Open
sergical wants to merge 1 commit into
Open
fix(tracing): Align cache token attributes with Sentry conventions#403sergical wants to merge 1 commit into
sergical wants to merge 1 commit into
Conversation
The Sentry AI Monitoring product reads `gen_ai.usage.input_tokens.cached` and `gen_ai.usage.input_tokens.cache_write`, but Junior was emitting the OTel-style names (`gen_ai.usage.cache_read.input_tokens` and `gen_ai.usage.cache_creation.input_tokens`). This made cache token data invisible in the AI Monitoring UI. Also adds `gen_ai.usage.total_tokens` which the agents traces table uses. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
gen_ai.usage.cache_read.input_tokens→gen_ai.usage.input_tokens.cachedandgen_ai.usage.cache_creation.input_tokens→gen_ai.usage.input_tokens.cache_writeto match the attribute names the Sentry AI Monitoring product reads.gen_ai.usage.total_tokenswhich the agents traces table queries viasum(gen_ai.usage.total_tokens).Context
Junior was emitting cache token span attributes using the OpenTelemetry spec names (
gen_ai.usage.cache_read.input_tokens/gen_ai.usage.cache_creation.input_tokens), but the Sentry product stack reads different attribute names:attributes.py):gen_ai.usage.input_tokens.cachedGEN_AI_USAGE_INPUT_TOKENS_CACHED = 'gen_ai.usage.input_tokens.cached'gen-ai-attributes.ts):GEN_AI_USAGE_INPUT_TOKENS_CACHED_ATTRIBUTE = 'gen_ai.usage.input_tokens.cached'The Sentry JS SDK's Vercel AI integration normalizes attributes to the Sentry convention names, but Junior uses
pi-ai'sstreamSimpledirectly (bypassing the Vercel AI SDK), so the SDK normalization never runs.This made cache token data invisible in the AI Monitoring UI — the data was being sent but the product never looked for those attribute names.
Test plan
extract-gen-ai-usage-summary.test.ts)🤖 Generated with Claude Code