feat: add GPT-Live adapter and playground - #50
Merged
Merged
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
alexanderqchen
marked this pull request as ready for review
September 21, 2026 13:08
This branch was successfully deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds a dedicated GPT-Live WebRTC adapter because Live uses a different session protocol and lifecycle from Realtime. New OpenAI integrations use Live in the homepage and documentation; existing Realtime integrations remain supported.
The website playground includes GPT-Live model settings and input/output diagnostics. Local testing can use a server-held credential restricted to same-origin loopback requests; deployed sessions require the caller's own key. Includes a minor-version changeset and roadmap update.
Validation: 76 unit tests, source/example/package/demo typechecks, lint, formatting, and package/demo builds pass. Browser checks exercise published exports and real local WebRTC; final CI is required before merge. Real OpenAI sessions verified audio, interruption, delegated responses, same-adapter restart, graceful final usage, and physical microphone playback in Chrome. Independent Live voice calibration remains outstanding.
AI-authored with Codex, directed by Alexander Chen to support GPT-Live, make it the primary OpenAI documentation path, and integrate it into the existing playground.
Need help on this PR? Tag
@codesmith-botwith what you need. Autofix is disabled.