Skip to content

fix(google): capture usage_metadata before early continues in streaming #5404

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

Open
Panmax wants to merge 2 commits into
base: main
Choose a base branch
from
+14 −14
Open

fix(google): capture usage_metadata before early continues in streaming #5404

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
22b8511
fix(google): move usage_metadata check before continue statements in …
Panmax Apr 10, 2026
18875bc
ci: retrigger checks
Panmax Apr 10, 2026
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
28 changes: 14 additions & 14 deletions livekit-plugins/livekit-plugins-google/livekit/plugins/google/llm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -464,6 +464,20 @@ async def _run(self) -> None:
request_id=request_id,
)

if response.usage_metadata is not None:
usage = response.usage_metadata
self._event_ch.send_nowait(
llm.ChatChunk(
id=request_id,
usage=llm.CompletionUsage(
completion_tokens=usage.candidates_token_count or 0,
prompt_tokens=usage.prompt_token_count or 0,
prompt_cached_tokens=usage.cached_content_token_count or 0,
total_tokens=usage.total_token_count or 0,
),
)
)

if not response.candidates:
continue

Expand Down Expand Up @@ -493,20 +507,6 @@ async def _run(self) -> None:
retryable = False
self._event_ch.send_nowait(chat_chunk)

if response.usage_metadata is not None:
usage = response.usage_metadata
self._event_ch.send_nowait(
llm.ChatChunk(
id=request_id,
usage=llm.CompletionUsage(
completion_tokens=usage.candidates_token_count or 0,
prompt_tokens=usage.prompt_token_count or 0,
prompt_cached_tokens=usage.cached_content_token_count or 0,
total_tokens=usage.total_token_count or 0,
),
)
)

if not response_generated:
raise APIStatusError(
"no response generated",
Expand Down
Loading