Skip to content

fix: emit cache token OTEL attributes as strings for Sentry #3501

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
lpcox merged 1 commit into from
May 21, 2026
Merged

fix: emit cache token OTEL attributes as strings for Sentry #3501

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 8 additions & 8 deletions containers/api-proxy/otel.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -445,21 +445,21 @@ function setTokenAttributes(span, { provider, model, normalizedUsage, streaming
span.setAttribute('gen_ai.response.model', model);
}
span.setAttributes({
// Standard GenAI semconv (Sentry recognizes these)
// Standard GenAI semconv (Sentry recognizes these as numeric)
'gen_ai.usage.input_tokens': normalizedUsage.input_tokens,
'gen_ai.usage.output_tokens': normalizedUsage.output_tokens,
'gen_ai.request.stream': streaming,
// Cache and reasoning — use Sentry measurement naming (no dots, _count suffix)
'cache_read_tokens_count': normalizedUsage.cache_read_tokens,
'cache_write_tokens_count': normalizedUsage.cache_write_tokens,
'reasoning_tokens_count': normalizedUsage.reasoning_tokens || 0,
// Cache and reasoning as strings (Sentry drops unknown numeric attrs but keeps strings)
Comment on lines +448 to +452
'awf.cache_read_tokens': String(normalizedUsage.cache_read_tokens),
'awf.cache_write_tokens': String(normalizedUsage.cache_write_tokens),
'awf.reasoning_tokens': String(normalizedUsage.reasoning_tokens || 0),
});
span.addEvent('gen_ai.usage', {
'gen_ai.usage.input_tokens': normalizedUsage.input_tokens,
'gen_ai.usage.output_tokens': normalizedUsage.output_tokens,
'cache_read_tokens_count': normalizedUsage.cache_read_tokens,
'cache_write_tokens_count': normalizedUsage.cache_write_tokens,
'reasoning_tokens_count': normalizedUsage.reasoning_tokens || 0,
'awf.cache_read_tokens': String(normalizedUsage.cache_read_tokens),
'awf.cache_write_tokens': String(normalizedUsage.cache_write_tokens),
'awf.reasoning_tokens': String(normalizedUsage.reasoning_tokens || 0),
});
} catch { /* best-effort */ }
}
Expand Down
8 changes: 4 additions & 4 deletions containers/api-proxy/otel.test.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -235,16 +235,16 @@ describe('otel — setTokenAttributes', () => {
expect(s.attributes['gen_ai.response.model']).toBe('gpt-4o');
expect(s.attributes['gen_ai.usage.input_tokens']).toBe(1000);
expect(s.attributes['gen_ai.usage.output_tokens']).toBe(500);
expect(s.attributes['cache_read_tokens_count']).toBe(200);
expect(s.attributes['cache_write_tokens_count']).toBe(50);
expect(s.attributes['awf.cache_read_tokens']).toBe('200');
expect(s.attributes['awf.cache_write_tokens']).toBe('50');
expect(s.attributes['gen_ai.request.stream']).toBe(false);

const usageEvent = s.events.find(e => e.name === 'gen_ai.usage');
expect(usageEvent).toBeDefined();
expect(usageEvent.attributes['gen_ai.usage.input_tokens']).toBe(1000);
expect(usageEvent.attributes['gen_ai.usage.output_tokens']).toBe(500);
expect(usageEvent.attributes['cache_read_tokens_count']).toBe(200);
expect(usageEvent.attributes['cache_write_tokens_count']).toBe(50);
expect(usageEvent.attributes['awf.cache_read_tokens']).toBe('200');
expect(usageEvent.attributes['awf.cache_write_tokens']).toBe('50');
Comment on lines 235 to +247
});

test('does not set gen_ai.response.model when model is "unknown"', async () => {
Expand Down
Loading