@layerwise-ai/invera-sdk changelog
All notable changes to the @layerwise-ai/invera-sdk TypeScript package.
The Python and TypeScript SDKs share one version and are released together.
[0.6.0] - 2026-10-02
- Breaking: the SDK now supports only invera Engines serving
Qwen/Qwen3.5-4B(tokenizer profileqwen3.5-4b, model familyqwen3_5).Qwen/Qwen3-4B-Instruct-2507is no longer supported. - Breaking: the
modelclient option is removed. The client always uses the release-pinned model profile; it cannot choose a model. - Breaking: requires Engine Contract
>=1.3.0 <2.0.0(was>=1.2.0 <2.0.0). - Breaking: tool calls are parsed only in the Qwen3.5 XML format
(
<function=…><parameter=…>…</parameter></function>); parameter values are typed from the tool's JSON schema. A malformed call is reported with the new schema issue codeinvalid_xml, which replacesinvalid_json. - The default Node.js tokenizer adapter now also registers tokens that a
tokenizer declares only in
tokenizer_config.json(such as the Qwen3.5 audio markers), so its special-token ids and decoding match Transformers. tool-descriptionmessages are display-only: the default tokenizer never renders them into the prompt. Pass tool definitions throughtools.
[0.5.2] - 2026-09-25
- New
apiKeyclient option: a static Engine API key sent asAuthorization: Bearer <key>on every Engine request.
[0.5.0] - 2026-09-22
- First release published to npm. The package is now named
@layerwise-ai/invera-sdk. - Licensed under the PolyForm Perimeter License 1.0.1 together with the Layerwise SDK Additional Permission; both texts ship in the package.
- The package README is reduced to name, version, vendor, documentation link, license pointer, and this changelog.
[0.4.3] - 2026-09-21
- Browser-safe
@layerwise-ai/invera-sdk/metadatasubpath that exposesSDK_VERSIONand the other public constants without Node-only imports. - The package declares
sideEffects: falseso bundlers can tree-shake it.
[0.4.2] - 2026-09-21
- The package manifest is exposed through the
./package.jsonexport.
[0.4.1] - 2026-09-17
- Output words are split at internal whitespace in attribution word mapping.
[0.4.0] - 2026-09-02
- Emitted attribution word mapping aligned between Python and TypeScript.
- Releases are gated by live Engine end-to-end checks.
- Documented the Node tokenizer container requirements.
[0.3.2] - 2026-08-25
- Supports invera Engine Contract 2.x on the v1 routes.
[0.3.1] - 2026-07-30
- Renamed to invera. Golden Path client, evidence stream, and the
advancedextension module.