Add Codex voice integration and agent-neutral onboarding - #55
Merged
Conversation
noisy
commented
Sep 5, 2026
| daily use). | ||
|
|
||
| ## Install in 2 minutes | ||
| ## Install for Codex |
Owner
Author
There was a problem hiding this comment.
Should this be before instructions for Claude? :D
Claude Code is the more common harness, so it leads. Codex support is labelled preview because the packaged install has not yet completed a spoken round trip from a fresh session - the code is verified, the onboarding is not.
noisy
marked this pull request as ready for review
September 5, 2026 04:22
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Codex voice sessions need their own identity and onboarding. This adds a Codex plugin, dedicated skill, and adapter around the existing shared hooks. Speech calls receive trusted per-session identity; configurable daemon selection and a reversible setup command keep hooks and MCP on the same endpoint. Chat headings use registered agent labels.
Legacy Claude servers ignore the new identity argument and preserve their existing routing. The Claude manifest and hook JSON are byte-identical to the base. Duplicate listeners now report a visible conflict without consuming speech.
Validation:
The synchronous Stop hook can hold a turn open for up to one hour; setup supports shorter or disabled idle listening. Hook trust remains a user review step. OpenAI voices and an idle queue/wake bridge are outside this PR.
Draft pending final review and a microphone/speaker round trip in a newly installed Codex session with trusted hooks. Automated packaging/routing checks do not establish audible playback or model consumption of trusted hook output. See docs/codex.md for installation and acceptance steps.