encounter/adk-python
0
0
Fork 0
mirror of https://github.com/encounter/adk-python.git synced 2026-03-30 10:57:20 -07:00
Code Issues Packages Projects Releases Wiki Activity

chore: Clean up the invocation context initialization logic for LIVE

Browse Source 
1. Removed dead code: The if not run_config.response_modalities: branch was never executed since run_live already sets the default (https://github.com/google/adk-python/blob/19de45b3250d09b9ec16c45788e7d472b3e588c2/src/google/adk/runners.py#L947-L948).
2. Simplified condition: Changed from checking 'TEXT' not in ... to 'AUDIO' in ...

Co-authored-by: Xiang (Sean) Zhou <seanzhougoogle@google.com>
PiperOrigin-RevId: 853274401
This commit is contained in:
Xiang (Sean) Zhou
2026-01-07 08:30:18 -08:00
committed by Copybara-Service
parent 96c5db5a07
commit d5bd8d939e
1 changed files with 3 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/google/adk/runners.py
+3 -11
View File
@@ -1381,23 +1381,15 @@ class Runner:
"""Creates a new invocation context for live multi-agent."""
run_config = run_config or RunConfig()
# For live multi-agent, we need model's text transcription as context for
# next agent.
# For live multi-agents system, we need model's text transcription as
# context for the transferred agent.
if self.agent.sub_agents and live_request_queue:
if not run_config.response_modalities:
# default
run_config.response_modalities = ['AUDIO']
if not run_config.output_audio_transcription:
run_config.output_audio_transcription = (
types.AudioTranscriptionConfig()
)
elif 'TEXT' not in run_config.response_modalities:
if 'AUDIO' in run_config.response_modalities:
if not run_config.output_audio_transcription:
run_config.output_audio_transcription = (
types.AudioTranscriptionConfig()
)
if not run_config.input_audio_transcription:
# need this input transcription for agent transferring in live mode.
run_config.input_audio_transcription = types.AudioTranscriptionConfig()
return self._new_invocation_context(
session,