Chat SDK now supports concurrent message handling
The Chat SDK now includes a new concurrency option for the Chat class that lets you control how incoming messages are handled while previous ones are processing. Choose from four strategies: drop (default, discards incoming), queue (processes latest after handler finishes), debounce (waits for pause, processes final message), or concurrent (processes immediately without locking).
now lets you control what happens when a new message arrives before a previous one finishes processing, with the new option for the Chat class.Chat SDKconcurrency
Four strategies are available:
Read the to get started.documentation
(default): discards incoming messages
drop: processes the latest message after the handler finishes
queue: waits for a pause in conversation, processes only the final message
debounce: processes every message immediately, no locking
concurrent
Source: original entry ↗
More from Vercel
Follow Vercel to get its new changes in your feed and email digest.
OpenAI Decisions API now available on AI Gateway
OpenAI's Decisions API is now accessible through Vercel's AI Gateway with an OpenAI-compatible endpoint, enabling decision models to answer typed questions and return probabilities, choices, and scores for routing, triage, and guardrails use cases. Support is available across the OpenAI SDK, AI SDK, HTTP API, and CLI with the latest versions.
Timestamp attributes now supported in Vercel Flags
Vercel Flags now supports timestamp attributes for entities, allowing you to create time-based targeting rules. Use this feature to run limited-time campaigns, show content between specific dates, or target users based on registration date.
Glyph Cluster now available in stealth on AI Gateway
Glyph Cluster, a reasoning model for coding and long-context analysis, is now available as a stealth model on Vercel's AI Gateway for Pro and Enterprise plan teams with purchased AI Gateway credits at no cost during the stealth period. The model supports function calling, streams responses, and can be accessed via AI SDK, OpenAI-compatible APIs, and coding agents.