Intel / repo

js-genai v2.31.0

Source: github.com
Author: release-please[bot]
Date: Published Oct 23, 2026

Why it matters

Adds Live API in-session context updates and audio, document and video content in function results, and raises mid-stream SSE errors consistently. These change what Gemini-based agents can do and how they fail.

Key takeaways · AI-distilled

js-genai 2.31.0 adds AudioContent, DocumentContent and VideoContent to FunctionResultSubContent, so function results sent back to Gemini can include audio, documents and video.
The Live API gains send__update for changing context inside an existing session, and LiveConnectConfig now accepts labels.
GenerateContentConfig adds a store option, available on the Gemini Developer API only, plus a new generation_output_config field.

Terms in this piece · Glossary

context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
multimodal — A model that works with more than text — reading images, audio, or video, and sometimes generating them too.

Read the source github.com