Skip to content

fix: remove LLMMetricAnnotation from response stream #1499

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
merged 4 commits into from
Jun 13, 2025
Merged

fix: remove LLMMetricAnnotation from response stream #1499

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
e98abe8
remove llmmetricannotation
tedzhouhk Jun 12, 2025
5670ca3
Update lib/llm/src/http/service/openai.rs
tedzhouhk Jun 12, 2025
fd4792e
Update lib/llm/src/http/service/openai.rs
tedzhouhk Jun 12, 2025
f6d6178
fix mut
tedzhouhk Jun 12, 2025
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
9 changes: 8 additions & 1 deletion lib/llm/src/http/service/openai.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -499,12 +499,19 @@ fn process_event_converter<T: Serialize>(
annotated: EventConverter<T>,
response_collector: &mut ResponseMetricCollector,
) -> Result<Event, axum::Error> {
let annotated = annotated.0;
let mut annotated = annotated.0;

// update metrics
if let Ok(Some(metrics)) = LLMMetricAnnotation::from_annotation(&annotated) {
response_collector.observe_current_osl(metrics.output_tokens);
response_collector.observe_response(metrics.input_tokens, metrics.chunk_tokens);

// Chomp the LLMMetricAnnotation so it's not returned in the response stream
// TODO: add a flag to control what is returned in the SSE stream
if annotated.event.as_deref() == Some(crate::preprocessor::ANNOTATION_LLM_METRICS) {
annotated.event = None;
annotated.comment = None;
}
}

let mut event = Event::default();
Expand Down
Loading