improve interruption handling, avoid agent from getting stuck #1290
+21
−5
Conversation
This file contains 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
🦋 Changeset detectedLatest commit: fda801b The changes in this PR will be included in the next version bump. This PR includes changesets to release 1 package
Not sure what this means? Click here to learn what changesets are. Click here if you're a maintainer who wants to add another changeset to this PR |
theomonnom
reviewed
Dec 24, 2024
theomonnom
approved these changes
Dec 24, 2024
This was referenced Dec 24, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
there are a couple of conditions that could cause the agent to be stuck. This is because the current speech could be interrupted first (because it's acting on VAD events), but the handling of that event only comes in later during validations.
this change ensures that if we ever get to the validation stage, and the agent is not currently speaking, we would always generate a new thread, even if the incoming transcript is empty. If interrupted with a cough (as an example), it will allow the agent to pick up from where it'd left off.
fixes #1229