TTS: gate auto audio on inbound voice notes #1667
Merged
Conversation
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
steipete
added a commit
that referenced
this pull request
Jan 25, 2026
3517f90 to
32d370e
Compare
32d370e to
4dfaec9
Compare
Contributor
|
Landed via temp rebase onto main.
Thanks @sebslight! |
jaydenfyi
pushed a commit
to jaydenfyi/clawdbot
that referenced
this pull request
Jan 25, 2026
Co-authored-by: Sebastian <[email protected]>
mcinteerj
pushed a commit
to mcinteerj/moltbot
that referenced
this pull request
Jan 25, 2026
Co-authored-by: Sebastian <[email protected]>
rodrigouroz
pushed a commit
to rodrigouroz/moltbot
that referenced
this pull request
Jan 26, 2026
Co-authored-by: Sebastian <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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
messages.tts.onlyWhenInboundAudiogate so auto‑TTS only runs when the last inbound message includes audio/voice.MediaType/MediaTypes,<media:audio>placeholder, or[Audio]transcript header and pass that flag into TTS dispatch.Why
We want a hard guarantee that audio replies only happen after an inbound voice note, rather than relying on model behavior.
Decisions
audio/*,<media:audio>placeholders, or[Audio]transcript marker.onlyWhenInboundAudiois missing, behavior is unchanged (auto‑TTS applies whenever TTS is enabled)./tts audioand explicit tool calls unaffected unless TTS is globally enabled; the new flag only gates auto‑TTS.Testing
pnpm test src/tts/tts.test.ts(runs full suite via test-parallel) ❌src/infra/heartbeat-runner.returns-default-unset.test.ts(expected WhatsApp sends were not triggered).src/tts/tts.test.tsitself passes.pnpm lint✅