Skip to content

fix: avoid duplicate token usage on llm fallback spans #7532

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

Draft
chenghao-mou wants to merge 1 commit into from
+8 −1
Draft

fix: avoid duplicate token usage on llm fallback spans #7532

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
3 changes: 2 additions & 1 deletion livekit-agents/livekit/agents/llm/llm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -433,7 +433,8 @@ async def _metrics_monitor_task(self, event_aiter: AsyncIterable[ChatChunk]) ->
)

# the GenAI response side; the request side was recorded at span creation
gen_ai_telemetry.set_usage_attributes(self._llm_request_span, metrics)
if self._genai_operation_name is not None:
gen_ai_telemetry.set_usage_attributes(self._llm_request_span, metrics)
finish_reason = gen_ai_telemetry.finish_reason_for(
function_calls=tool_calls, interrupted=metrics.cancelled
)
Expand Down
6 changes: 6 additions & 0 deletions tests/test_llm_telemetry.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -170,6 +170,12 @@ async def test_llm_span_reports_cached_input_tokens(
if (span.attributes or {}).get(trace_types.ATTR_GEN_AI_OPERATION_NAME) == "chat"
]
assert [span.name for span in inference_spans] == ["llm_request"]
usage_spans = [
span
for span in finished_spans
if any(key.startswith("gen_ai.usage.") for key in (span.attributes or {}))
]
assert usage_spans == inference_spans
spans = [span for span in finished_spans if span.name == "llm_request"]
assert len(spans) == 1
assert spans[0].attributes["gen_ai.usage.input_tokens"] == 100
Expand Down
Loading