broker: REASONING_EFFORT knob for reasoning-line Realtime models - #7
Draft
jayzuccarelli wants to merge 1 commit into
Draft
broker: REASONING_EFFORT knob for reasoning-line Realtime models#7jayzuccarelli wants to merge 1 commit into
jayzuccarelli wants to merge 1 commit into
Conversation
gpt-realtime-2.1 is a reasoning-line model; its server default effort (low) pads spoken replies and adds latency. Pipecat 0.0.97's SessionProperties has no reasoning field and pydantic serializes by declared type, so the broker injects reasoning.effort into the session.update wire dict when REASONING_EFFORT is set. Unset = field not sent (required for non-reasoning models like gpt-realtime); zero behavior change by default. Benched 2026-07-21 (isolated 8766/8767, hygiene off, paired same-hour runs): minimal effort fixes 2.1's verbosity (one-liner replies) but first-audio p50 stays 500-680ms vs 97-292ms on live gpt-realtime, so the live model keeps MODEL=gpt-realtime for now. Part of JAY-92. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
Important Review skippedDraft detected. Please check the settings in the CodeRabbit UI or the ⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Plus Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
jayzuccarelli
force-pushed
the
reasoning-effort-knob
branch
from
August 14, 2026 21:15
4e73fe7 to
b32c4ef
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Adds a
REASONING_EFFORTenv knob (minimal/low/medium/high/xhigh) that injectsreasoning: {effort}into everysession.update. Pipecat 0.0.97'sSessionPropertieshas noreasoningfield and pydantic serializes by declared type, so the broker's service subclass injects it into the wire dict insend_client_event. Unset = field not sent (required for non-reasoning models likegpt-realtime); zero behavior change by default.Why
gpt-realtime-2.1is a reasoning-line Realtime model; its server-default effort (low) pads spoken replies and adds latency. This knob makes 2.1-line models testable/usable without prompt hacks.Bench (2026-07-21, isolated 8766/8767, hygiene off, paired same-hour runs)
gpt-realtime(live)gpt-realtime-2.1+minimalVerdict: minimal effort fixes 2.1's wordiness but 2.1 stays ~400-500ms behind on first-audio in this stack, so live keeps
MODEL=gpt-realtime.🤖 Generated with Claude Code