Chat SDK now supports rich text in Telegram
The Chat SDK now renders markdown and AST messages as native rich text on Telegram, enabling real headings, lists, tables, task lists, formulas, and media blocks instead of flattened text. Existing plain string and card formats continue to work automatically with fallback support.
Chat SDK now renders explicit and messages as native rich messages on the . Your bots get real headings, lists, tables, task lists, formulas, and separate media blocks instead of flattened text.markdownastTelegram adapter
What you get:
Read the to get started.Telegram adapter documentation
: headings, lists, tables, task lists, formulas, and media blocks.Native formatting
: private chats show live draft previews and persist the final response.Streaming
: plain strings, raw messages, cards, and captions continue to work exactly as before.Automatic fallback
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.