Skip to content

release/0.1: add scene3 and bump to 0.1.43 - #86

Merged
LingXuanYin merged 3 commits into
release/0.1from
chore/bump-0.1.43
Oct 28, 2026
Merged

LingXuanYin merged 3 commits into
release/0.1from
chore/bump-0.1.43

Conversation

@LingXuanYin

@LingXuanYin LingXuanYin commented Oct 28, 2026 •

Copy link
Copy Markdown
Collaborator

Summary

The 0.1 line, for dependents still on ^0.1.x: the scene3 model and the 0.1.43 version, on a new release/0.1 branch cut from the 0.1.42 release commit.

 release/0.1 = 1e3b000 (0.1.42)
+  d8b00df feat: add the scene3 text-to-speech model
+  599e93a docs: name scene3 in the TTS model choice notes
+  2eb6d93 chore: bump generation SDK version to 0.1.43

These are the commits of #85 before its rebase onto main; main carries the same change on the 0.2 line. 0.1.43 is published under the dist-tag release-0.1, so latest stays on the 0.2 line.

Evidence

  • On 2eb6d93, exported without line-ending conversion, in node:24-slim: pnpm lint checks 72 files with no errors, typecheck passes, vitest 413 passed (19 files), build completes.
  • The scene3 tests are the ones in feat: add the scene3 text-to-speech model #85.
  • Added lines, file names and commit messages were scanned for internal names: clean.

Merge Danger

Door: two-way for the code; a published version stays.

Blast Radius: none for existing callers; 0.1.43 only adds scene3 to 0.1.42.

scene3 speaks one text block, where inline [bracketed] cues such as [sighs] or [laughs] direct the delivery, and can clone one HTTP(S) reference recording. The audio block's meta.text may carry that recording's transcript; the request goes to /v1/audio/speech with the reference in metadata.references.
scene3 is used when the user or an external policy names it; the Qwen defaults are unchanged. The rejection tests already pin each message exactly, so the extra pattern check is dropped.
Release 0.1.43: adds the `scene3` text-to-speech model, with inline [bracketed] delivery cues and an optional one-reference clone whose transcript can ride on the audio block's meta.text. The qwen speech models are unchanged.
@LingXuanYin LingXuanYin changed the title chore: bump generation SDK version to 0.1.43 release/0.1: add scene3 and bump to 0.1.43 Oct 28, 2026
@LingXuanYin
LingXuanYin changed the base branch from feat/scene3 to release/0.1 October 28, 2026 01:32
@LingXuanYin
LingXuanYin merged commit e09a668 into release/0.1 Oct 28, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant