feat!: prepare AIWrapper 4.0.0 with live and speech APIs - #21
Merged
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This prepares AIWrapper 4.0.0 by merging the full
refactor-july-2026branch intomain. Applications gain persistent live model sessions, streaming speech providers, realtime voice agents, and native AWS Bedrock support, alongside fixes to provider streaming, cancellation, tool results, and agent lifecycle handling.The package now uses the published
aimodels0.7.0 catalog (^0.7.0). The browser playground adds chat, transcription, synthesis, and live voice flows with shared provider settings and server-owned sessions. Build and CI checks cover the ESM package and browser playground, with credential-backed integration tests separated from deterministic checks.Breaking changes and migration
aiwrapper,aiwrapper/bedrock, andaiwrapper/speech. Undeclared deep imports are no longer exposed.LangVecsAPI; callers must migrate embedding functionality before upgrading.Speech2Text.openai(...).ask(file)withSpeechToText.openai(...)and its audio session API (createSession,appendAudio, andfinish).TextToSpeech.elevenlabs(...).ask(text)object-URL result with the streamingspeak(...)API. Supply an explicitvoiceIdand usevoiceSettingsin place ofvoice_settings.@aws-sdk/client-bedrock-runtimepeer and pass a configured client when using Bedrock. Direct browser requests remain subject to provider CORS support; privileged credentials should stay on the server.See speech and live providers, realtime agents, and Bedrock for usage details.
Validation
npm run check: package build, 177 unit tests, and package dry run passed with version 4.0.0.npm run check:playground: type check (zero errors or warnings), 35 tests, and production build passed with publishedaimodels0.7.0; the subsequent change only updates the root package version.git diff --checkpassed for the release preparation changes.This PR updates the package version without creating a release tag. The npm publish workflow runs when a
v*tag is pushed.