Skip S1-mini cleanup for text bound for Speak targets - #149
Merged
Merged
Conversation
JRufer
added this pull request to stack #154
September 24, 2026 01:24
JRufer
force-pushed
the
feat/speak-skip-s1-mini
branch
from
September 24, 2026 01:28
456812c to
a32d87f
Compare
Base automatically changed from
feat/interim-command-detection
to
development
September 24, 2026 01:33
Speak targets read their text aloud verbatim, so the S1-mini rewrite only adds latency before the first word and can change what the user meant to have spoken. Command resolution now picks the target and raw text first and runs S1-mini once afterwards, instead of repeating the check per branch. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
JRufer
force-pushed
the
feat/speak-skip-s1-mini
branch
from
September 24, 2026 01:33
a32d87f to
8ead838
Compare
6 tasks
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Part 3 of re-landing 1f13d62. Stacked on #148 (base
feat/interim-command-detection; itself on #147). Both PRs edit the same routing block in the delivery worker, so this one is rebased on it to avoid a merge conflict.Text going to a Speak target is read aloud word for word, so S1-mini cleanup is now skipped for it. The cleanup delays the first spoken word and can reword what the user meant to have said.
Command resolution now decides
(target, raw text)first, then runs S1-mini once. The original commit repeated the Speak check in four places.Test plan
cargo test -p voxctrl-app: 92 pass🤖 Generated with Claude Code