Skip to content

Comment out adaptive interruption mode #113

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
aryeila merged 4 commits into from
Oct 19, 2026
Merged

Comment out adaptive interruption mode #113

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
c5ea5c6
Comment out adaptive interruption mode
aryeila Oct 19, 2026
1c8f505
Clarify when to uncomment adaptive interruption mode
aryeila Oct 19, 2026
b26762d
Name the line to uncomment in the adaptive interruption comment
aryeila Oct 19, 2026
849e311
Restore the README feature bullet
aryeila Oct 19, 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
5 changes: 4 additions & 1 deletion src/agent.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -126,7 +126,10 @@ async def my_agent(ctx: JobContext):
turn_detection=inference.TurnDetector(),
# Adaptive interruptions use the turn detector to tell a real interruption from a
# backchannel like "mhm" or "right", so the agent keeps talking through the latter.
interruption={"mode": "adaptive"},
# This model is on by default on LiveKit Cloud and in dev mode. To use the model elsewhere,
# uncomment the `interruption` line. Self-hosted usage past the monthly allowance is billed.
# See https://docs.livekit.io/deploy/admin/quotas-and-limits/#adaptive-interruption-handling for more information.
# interruption={"mode": "adaptive"},
# allow the LLM to generate a response while waiting for the end of turn
# See more at https://docs.livekit.io/agents/build/audio/#preemptive-generation
preemptive_generation={"enabled": True},
Expand Down
Loading