Skip to content

fix: ensure interrupted signal is emitted when flushing text in GeminiLlmConnection #4677

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

Closed
vonhutuan-b3 wants to merge 7 commits into from
Closed

fix: ensure interrupted signal is emitted when flushing text in GeminiLlmConnection #4677

Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
99f98b0
fix: ensure interrupted signal is emitted when flushing text in Gemin…
vonhutuan-b3 Mar 2, 2026
1f7a004
fix: avoid duplicate interruption signals
vonhutuan-b3 Mar 2, 2026
3b96ed8
Merge branch 'main' into fix-interruption-signal
rohityan Mar 4, 2026
2c2d208
Merge branch 'main' into fix-interruption-signal
vonhutuan-b3 Mar 12, 2026
b89f285
Merge branch 'main' into fix-interruption-signal
rohityan Mar 20, 2026
b6f43e7
Merge branch 'main' into fix-interruption-signal
vonhutuan-b3 Mar 27, 2026
35bbbb1
Merge branch 'main' into fix-interruption-signal
wuliang229 Apr 17, 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
12 changes: 5 additions & 7 deletions src/google/adk/models/gemini_llm_connection.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -220,7 +220,6 @@ async def receive(self) -> AsyncGenerator[LlmResponse, None]:
if content and content.parts:
llm_response = LlmResponse(
content=content,
interrupted=message.server_content.interrupted,
model_version=self._model_version,
live_session_id=live_session_id,
)
Expand Down Expand Up @@ -351,12 +350,11 @@ async def receive(self) -> AsyncGenerator[LlmResponse, None]:
if text:
yield self.__build_full_text_response(text)
text = ''
else:
yield LlmResponse(
interrupted=message.server_content.interrupted,
model_version=self._model_version,
live_session_id=live_session_id,
)
yield LlmResponse(
interrupted=message.server_content.interrupted,
model_version=self._model_version,
live_session_id=live_session_id，
)
if message.tool_call:
logger.debug('Received tool call: %s', message.tool_call)
if text:
Expand Down