Skip to content

fix(gateway): keep transcript echoes opt-in - #53313

Closed
chriswinig wants to merge 1 commit into
NousResearch:mainfrom
chriswinig:chris/transcript-echo-opt-in
Closed

fix(gateway): keep transcript echoes opt-in#53313
chriswinig wants to merge 1 commit into
NousResearch:mainfrom
chriswinig:chris/transcript-echo-opt-in

Conversation

@chriswinig

Copy link
Copy Markdown

Summary

  • stops automatic raw STT transcript echo unless stt_echo_transcripts is explicitly enabled
  • keeps transcript content prepended to the agent input, avoiding duplicate Telegram replies for transcribe/translate voice messages
  • applies the same behavior to mid-turn voice interrupts

Test plan

  • python -m compileall -q gateway

@chriswinig
chriswinig force-pushed the chris/transcript-echo-opt-in branch from 577a96a to 4f6a52d Compare June 26, 2026 23:05
@alt-glitch alt-glitch added type/feature New feature or request comp/gateway Gateway runner, session dispatch, delivery platform/telegram Telegram bot adapter tool/tts Text-to-speech and transcription P3 Low — cosmetic, nice to have labels Jun 26, 2026
@teknium1

teknium1 commented Jul 5, 2026

Copy link
Copy Markdown
Contributor

Superseded by PR #58859, which makes the transcript echo configurable via stt.echo_transcripts instead of flipping it to opt-in unconditionally — hard-disabling the echo by default would silently change behavior for users who rely on it. The config route gives your deployment the same outcome (stt.echo_transcripts: false). Thanks for flagging the noise issue!

@teknium1 teknium1 closed this Jul 5, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

comp/gateway Gateway runner, session dispatch, delivery P3 Low — cosmetic, nice to have platform/telegram Telegram bot adapter tool/tts Text-to-speech and transcription type/feature New feature or request

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants