mirror of
https://github.com/vercel/chat.git
synced 2026-09-14 18:32:29 +08:00
Raimond Lume
2700ce85b3
* feat(chat): Enable disabling code-fencing for streamed tables per-adapter As Slack now natively supports markdown tables, the code-fencing for tables is not required and in fact stops them from being rendered natively. This PR adds an option to configure code-fencing tables per adapter. By default true, false only for Slack. * Update StreamingMarkdownRendererOptions comments Removed comment about default behavior for wrapTablesForAppend option.
chat
Core SDK for building multi-platform chat bots. Provides the Chat class, event handlers, JSX card runtime, emoji helpers, and type-safe message formatting.
Installation
npm install chat
Usage
import { Chat } from "chat";
import { createSlackAdapter } from "@chat-adapter/slack";
import { createRedisState } from "@chat-adapter/state-redis";
const bot = new Chat({
userName: "mybot",
adapters: {
slack: createSlackAdapter({
botToken: process.env.SLACK_BOT_TOKEN!,
signingSecret: process.env.SLACK_SIGNING_SECRET!,
}),
},
state: createRedisState({ url: process.env.REDIS_URL! }),
dedupeTtlMs: 600_000, // 10 minutes (default: 5 min)
});
bot.onNewMention(async (thread) => {
await thread.subscribe();
await thread.post("Hello! I'm listening to this thread.");
});
bot.onSubscribedMessage(async (thread, message) => {
await thread.post(`You said: ${message.text}`);
});
Tip: PostgreSQL and ioredis adapters are also available for production. See State Adapters for all options.
Configuration
| Option | Type | Default | Description |
|---|---|---|---|
userName |
string |
required | Default bot username across all adapters |
adapters |
Record<string, Adapter> |
required | Map of adapter name to adapter instance |
state |
StateAdapter |
required | State adapter for subscriptions, locking, and dedup |
logger |
Logger | LogLevel |
"info" |
Logger instance or log level ("silent" to disable) |
streamingUpdateIntervalMs |
number |
500 |
Update interval for fallback streaming (post + edit) in ms |
dedupeTtlMs |
number |
300000 |
TTL for message deduplication entries in ms. Increase if webhook cold starts cause platform retries (e.g., Slack's http_timeout retry) that arrive after the default window |
AI coding agent support
If you use an AI coding agent like Claude Code, you can teach it about Chat SDK:
npx skills add vercel/chat
Documentation
Full documentation is available at chat-sdk.dev/docs.
- Usage — event handlers, threads, messages, channels
- Chat API — full
Chatclass reference - Cards — JSX-based interactive cards
- Streaming — AI SDK integration
- Emoji — cross-platform emoji helpers
License
MIT