This PR was opened by the [Changesets release](https://github.com/changesets/action) GitHub action. When you're ready to do a release, you can merge this and the packages will be published to npm automatically. If you're not ready to do a release yet, that's fine, whenever you add more changesets to main, this PR will be updated. # Releases ## @chat-adapter/discord@4.34.0 ### Minor Changes -0fdb902: Add opt-in Discord Components v2 rendering for Chat SDK cards via `contentFormat: DiscordContentFormat.ComponentsV2`. -5341f90: Ignore `@everyone`/`@here` pings by default in gateway mode. Previously the legacy gateway listener treated global pings as bot mentions, so the bot responded to announcements. A new `respondToGlobalMentions` config option (default `false`) restores the old behavior when enabled, and also lets forwarded gateway messages opt in via the `mention_everyone` field. -6c2a391: Add support for renaming native Discord thread channels. ### Patch Changes - Updated dependencies [5c926f1] - Updated dependencies [2531a42] - Updated dependencies [1721fa0] - Updated dependencies [4717a38] - Updated dependencies [6714efc] - chat@4.34.0 - @chat-adapter/shared@4.34.0 ## @chat-adapter/slack@4.34.0 ### Minor Changes -1721fa0: Add support for Slack's Agent messaging experience (`agent_view`). - New core event `onAppContextChanged` with a normalized `AppContextEntity[]` describing the user's active view (channel / canvas / list / message / unknown). - `AppHomeOpenedEvent` now carries the folded active-view context as `entities` and the opened `tab` (Slack: `"home"` / `"messages"`), so handlers can tell a Home-tab open from the DM-open signal under `agent_view`. - Slack adapter: new `agentView` config flag (under `agent_view`, `app_home_opened` is the DM-open signal regardless of tab and folded context is surfaced), routing for the `app_context_changed` event, and a `getAppContext(message)` helper to read the folded context on DM messages. - `setSuggestedPrompts` now accepts an optional thread reference (agent_view lets prompts sit at the top of the agent conversation). - Under `agentView`, DM (Messages-tab) messages are threaded per new Slack's model — each user message is a thread root (`thread_ts ?? ts`). Conversation-scoped threads returned by `openDM()` keep working: when that thread is subscribed, incoming top-level DM messages route to it. - `createSlackAdapter` env auth fallback (`SLACK_BOT_TOKEN` / `SLACK_CLIENT_ID` / `SLACK_CLIENT_SECRET`) is now disabled only when an auth or verification field (`botToken`, `clientId`, `clientSecret`, `installationProvider`, `signingSecret`, `webhookVerifier`) is passed explicitly, instead of by any config object — so `createSlackAdapter({ agentView: true })` still picks up env credentials, while explicit-secret configs stay immune to ambient env vars. - Bumped `@slack/web-api` to `^7.18.0` (adds the optional `thread_ts` typing for `setSuggestedPrompts`). -4717a38: Add chart support and richer table rendering, with native Slack data table and data visualization blocks. - New core `ChartElement` and `Chart()` builder (JSX supported) with pie, bar, area, and line charts, mirroring Slack's data visualization model: pie charts take `segments`, series charts take named `series` plotted against shared `categories` with optional `xLabel`/`yLabel`. - `TableElement` / `Table()` gain optional `caption` (accessible table description) and `pageSize` (rows per page) fields. - Charts degrade gracefully on platforms without native chart support: the underlying data renders as a text table via the shared card fallback (new `chartElementToFallbackText` helper). - Slack adapter: card tables now render as [data table blocks](https://docs.slack.dev/reference/block-kit/blocks/data-table-block) by default — paginated and sortable — instead of plain table blocks. Header-only tables keep the plain table block; tables exceeding Slack limits (100 data rows, 20 columns, 10,000 characters) fall back to ASCII as before. - Slack adapter: card charts render as [data visualization blocks](https://docs.slack.dev/reference/block-kit/blocks/data-visualization-block). Charts violating Slack constraints (50-character title, 12 segments/series, 20 categories, 20-character labels, one data point per category, max 2 charts per message) fall back to a text rendering instead of being rejected by the API. - The `@chat-adapter/slack/blocks` subpath gets the same treatment: `SlackChartElement` types, `chart` card children, data table rendering, and matching limits. - `postMessage` now surfaces Slack's per-block validation details when the API rejects blocks (`invalid_blocks`), instead of the bare "An API error occurred" message. -0f743c9: Add declarative agent-experience config and harden native streaming: - `suggestedPrompts` — a static payload or per-thread resolver, applied automatically when an assistant/agent thread opens (`assistant_thread_started` in legacy `assistant_view`, or a Messages-tab `app_home_opened` under `agentView`, where prompts pin at the top of the agent conversation without a `thread_ts`). The resolver receives the thread context (`channelId`, `userId`, legacy `threadTs`/`teamId`/`enterpriseId`, and active-view `entities` under `agentView`); returning `null`/`undefined` skips the thread. Prompts beyond Slack's 4-prompt limit are dropped with a warning, and resolver/API failures are logged without failing the webhook. - `loadingMessages` — default rotating status strings for the assistant thinking indicator, used by `startTyping` and `setAssistantStatus` when no explicit status/messages are passed. - `nativeStreaming` config (default `true`). Set `false` on Slack flavours without the `chat.startStream` family (e.g. GovSlack) to always stream via post-and-edit. - If the workspace rejects the first native streaming call, `stream()` now falls back to throttled post-and-edit mid-stream instead of failing the reply; already-consumed text is preserved. Permanent platform errors (`unknown_method`, `method_deprecated`, `feature_not_enabled`) latch native streaming off for subsequent streams on the adapter instance. Structured chunks (`task_update` / `plan_update`) are skipped in fallback mode. - `feedbackButtons` — append Slack's native thumbs up/down (`context_actions` + `feedback_buttons` block) to every streamed reply. Pass `true` for defaults or an options object (`actionId`, labels, values); clicks dispatch through `bot.onAction` with a positive/negative value. A `buildFeedbackButtonsBlock(options?)` helper is exported for attaching the block to non-streamed messages. New exported types: `SlackFeedbackButtonsOptions`, `SlackSuggestedPrompt`, `SlackSuggestedPrompts`, `SlackSuggestedPromptsContext`, `SlackSuggestedPromptsOptions`. ### Patch Changes - Updated dependencies [5c926f1] - Updated dependencies [2531a42] - Updated dependencies [1721fa0] - Updated dependencies [4717a38] - Updated dependencies [6714efc] - chat@4.34.0 - @chat-adapter/shared@4.34.0 ## @chat-adapter/telegram@4.34.0 ### Minor Changes -8d7ccdb: Add Telegram media group uploads for multiple files and attachments. ### Patch Changes -2531a42: Fix `detectMention` (and the Telegram adapter's `isBotMentioned`) falsely matching `@bot` when `@bot-dev` is mentioned. `\b` (word boundary) matches between a word character and a hyphen, so `/@bot\b/` incorrectly matches `@bot-dev`. Replaced with `(?![\w-])` to exclude hyphens. - Updated dependencies [5c926f1] - Updated dependencies [2531a42] - Updated dependencies [1721fa0] - Updated dependencies [4717a38] - Updated dependencies [6714efc] - chat@4.34.0 - @chat-adapter/shared@4.34.0 ## @chat-adapter/web@4.34.0 ### Minor Changes -6714efc: Support AI SDK v7 as a peer dependency. - `chat` now accepts `ai@^6.0.182 || ^7.0.0` (`chat/ai` tools work with both majors). - `@chat-adapter/web` now accepts `ai@^6 || ^7`, `@ai-sdk/react@^3 || ^4`, `@ai-sdk/svelte@^4 || ^5`, and `@ai-sdk/vue@^3 || ^4`. - The `chat/ai` tool factories now declare explicit `Tool<Input, Output>` return types instead of relying on inference, so the published declarations no longer depend on `ai` internals that changed in v7. The public type surface is unchanged. ### Patch Changes - Updated dependencies [5c926f1] - Updated dependencies [2531a42] - Updated dependencies [1721fa0] - Updated dependencies [4717a38] - Updated dependencies [6714efc] - chat@4.34.0 - @chat-adapter/shared@4.34.0 ## @chat-adapter/whatsapp@4.34.0 ### Minor Changes -2338a66: Add `sendTemplate()` for sending pre-approved template messages, enabling business-initiated conversations outside the 24-hour customer service window -8bd8a57: Implement outbound file and attachment sending for the WhatsApp adapter. Supports binary `FileUpload` uploads, typed `Attachment` payloads (binary or HTTPS link passthrough), multi-file sequential sends, smart MIME-to-message-type mapping, caption placement with audio/long-text fallbacks, and card+file sequencing. ### Patch Changes - Updated dependencies [5c926f1] - Updated dependencies [2531a42] - Updated dependencies [1721fa0] - Updated dependencies [4717a38] - Updated dependencies [6714efc] - chat@4.34.0 - @chat-adapter/shared@4.34.0 ## @chat-adapter/x@4.34.0 ### Minor Changes -4bca64f: add image upload support to X posts and DMs via the chunked media upload endpoints ### Patch Changes - Updated dependencies [5c926f1] - Updated dependencies [2531a42] - Updated dependencies [1721fa0] - Updated dependencies [4717a38] - Updated dependencies [6714efc] - chat@4.34.0 - @chat-adapter/shared@4.34.0 ## chat@4.34.0 ### Minor Changes -1721fa0: Add support for Slack's Agent messaging experience (`agent_view`). - New core event `onAppContextChanged` with a normalized `AppContextEntity[]` describing the user's active view (channel / canvas / list / message / unknown). - `AppHomeOpenedEvent` now carries the folded active-view context as `entities` and the opened `tab` (Slack: `"home"` / `"messages"`), so handlers can tell a Home-tab open from the DM-open signal under `agent_view`. - Slack adapter: new `agentView` config flag (under `agent_view`, `app_home_opened` is the DM-open signal regardless of tab and folded context is surfaced), routing for the `app_context_changed` event, and a `getAppContext(message)` helper to read the folded context on DM messages. - `setSuggestedPrompts` now accepts an optional thread reference (agent_view lets prompts sit at the top of the agent conversation). - Under `agentView`, DM (Messages-tab) messages are threaded per new Slack's model — each user message is a thread root (`thread_ts ?? ts`). Conversation-scoped threads returned by `openDM()` keep working: when that thread is subscribed, incoming top-level DM messages route to it. - `createSlackAdapter` env auth fallback (`SLACK_BOT_TOKEN` / `SLACK_CLIENT_ID` / `SLACK_CLIENT_SECRET`) is now disabled only when an auth or verification field (`botToken`, `clientId`, `clientSecret`, `installationProvider`, `signingSecret`, `webhookVerifier`) is passed explicitly, instead of by any config object — so `createSlackAdapter({ agentView: true })` still picks up env credentials, while explicit-secret configs stay immune to ambient env vars. - Bumped `@slack/web-api` to `^7.18.0` (adds the optional `thread_ts` typing for `setSuggestedPrompts`). -4717a38: Add chart support and richer table rendering, with native Slack data table and data visualization blocks. - New core `ChartElement` and `Chart()` builder (JSX supported) with pie, bar, area, and line charts, mirroring Slack's data visualization model: pie charts take `segments`, series charts take named `series` plotted against shared `categories` with optional `xLabel`/`yLabel`. - `TableElement` / `Table()` gain optional `caption` (accessible table description) and `pageSize` (rows per page) fields. - Charts degrade gracefully on platforms without native chart support: the underlying data renders as a text table via the shared card fallback (new `chartElementToFallbackText` helper). - Slack adapter: card tables now render as [data table blocks](https://docs.slack.dev/reference/block-kit/blocks/data-table-block) by default — paginated and sortable — instead of plain table blocks. Header-only tables keep the plain table block; tables exceeding Slack limits (100 data rows, 20 columns, 10,000 characters) fall back to ASCII as before. - Slack adapter: card charts render as [data visualization blocks](https://docs.slack.dev/reference/block-kit/blocks/data-visualization-block). Charts violating Slack constraints (50-character title, 12 segments/series, 20 categories, 20-character labels, one data point per category, max 2 charts per message) fall back to a text rendering instead of being rejected by the API. - The `@chat-adapter/slack/blocks` subpath gets the same treatment: `SlackChartElement` types, `chart` card children, data table rendering, and matching limits. - `postMessage` now surfaces Slack's per-block validation details when the API rejects blocks (`invalid_blocks`), instead of the bare "An API error occurred" message. -6714efc: Support AI SDK v7 as a peer dependency. - `chat` now accepts `ai@^6.0.182 || ^7.0.0` (`chat/ai` tools work with both majors). - `@chat-adapter/web` now accepts `ai@^6 || ^7`, `@ai-sdk/react@^3 || ^4`, `@ai-sdk/svelte@^4 || ^5`, and `@ai-sdk/vue@^3 || ^4`. - The `chat/ai` tool factories now declare explicit `Tool<Input, Output>` return types instead of relying on inference, so the published declarations no longer depend on `ai` internals that changed in v7. The public type surface is unchanged. ### Patch Changes -5c926f1: Preserve markdown structural whitespace when extracting normalized message text. -2531a42: Fix `detectMention` (and the Telegram adapter's `isBotMentioned`) falsely matching `@bot` when `@bot-dev` is mentioned. `\b` (word boundary) matches between a word character and a hyphen, so `/@bot\b/` incorrectly matches `@bot-dev`. Replaced with `(?![\w-])` to exclude hyphens. ## @chat-adapter/gchat@4.34.0 ### Patch Changes - Updated dependencies [5c926f1] - Updated dependencies [2531a42] - Updated dependencies [1721fa0] - Updated dependencies [4717a38] - Updated dependencies [6714efc] - chat@4.34.0 - @chat-adapter/shared@4.34.0 ## @chat-adapter/github@4.34.0 ### Patch Changes - Updated dependencies [5c926f1] - Updated dependencies [2531a42] - Updated dependencies [1721fa0] - Updated dependencies [4717a38] - Updated dependencies [6714efc] - chat@4.34.0 - @chat-adapter/shared@4.34.0 ## @chat-adapter/linear@4.34.0 ### Patch Changes - Updated dependencies [5c926f1] - Updated dependencies [2531a42] - Updated dependencies [1721fa0] - Updated dependencies [4717a38] - Updated dependencies [6714efc] - chat@4.34.0 - @chat-adapter/shared@4.34.0 ## @chat-adapter/messenger@4.34.0 ### Patch Changes - Updated dependencies [5c926f1] - Updated dependencies [2531a42] - Updated dependencies [1721fa0] - Updated dependencies [4717a38] - Updated dependencies [6714efc] - chat@4.34.0 - @chat-adapter/shared@4.34.0 ## @chat-adapter/shared@4.34.0 ### Patch Changes - Updated dependencies [5c926f1] - Updated dependencies [2531a42] - Updated dependencies [1721fa0] - Updated dependencies [4717a38] - Updated dependencies [6714efc] - chat@4.34.0 ## @chat-adapter/teams@4.34.0 ### Patch Changes - Updated dependencies [5c926f1] - Updated dependencies [2531a42] - Updated dependencies [1721fa0] - Updated dependencies [4717a38] - Updated dependencies [6714efc] - chat@4.34.0 - @chat-adapter/shared@4.34.0 ## @chat-adapter/twilio@4.34.0 ### Patch Changes - Updated dependencies [5c926f1] - Updated dependencies [2531a42] - Updated dependencies [1721fa0] - Updated dependencies [4717a38] - Updated dependencies [6714efc] - chat@4.34.0 - @chat-adapter/shared@4.34.0 ## @chat-adapter/state-ioredis@4.34.0 ### Patch Changes - Updated dependencies [5c926f1] - Updated dependencies [2531a42] - Updated dependencies [1721fa0] - Updated dependencies [4717a38] - Updated dependencies [6714efc] - chat@4.34.0 ## @chat-adapter/state-memory@4.34.0 ### Patch Changes - Updated dependencies [5c926f1] - Updated dependencies [2531a42] - Updated dependencies [1721fa0] - Updated dependencies [4717a38] - Updated dependencies [6714efc] - chat@4.34.0 ## @chat-adapter/state-pg@4.34.0 ### Patch Changes - Updated dependencies [5c926f1] - Updated dependencies [2531a42] - Updated dependencies [1721fa0] - Updated dependencies [4717a38] - Updated dependencies [6714efc] - chat@4.34.0 ## @chat-adapter/state-redis@4.34.0 ### Patch Changes - Updated dependencies [5c926f1] - Updated dependencies [2531a42] - Updated dependencies [1721fa0] - Updated dependencies [4717a38] - Updated dependencies [6714efc] - chat@4.34.0 ## @chat-adapter/tests@4.34.0 Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
@chat-adapter/x
npm package:
@chat-adapter/x
X (Twitter) adapter for Chat SDK, using the X API v2 and the X Activity API. Reply to public mentions, hold DM conversations, post from the bot account, and like posts.
Documentation: chat-sdk.dev/adapters/official/x · Guides: vercel.com/kb/chat-sdk
Installation
pnpm add @chat-adapter/x
Scaffold with the CLI
To scaffold a new X bot with this adapter preselected:
npx create-chat-sdk@latest my-bot --adapter x memory
Visit the adapters directory to see other available official and vendor-official adapters.
Usage
import { Chat } from "chat";
import { createXAdapter } from "@chat-adapter/x";
const bot = new Chat({
userName: "mybot",
adapters: {
x: createXAdapter(),
},
});
bot.onNewMention(async (thread, message) => {
await thread.post(`Hi @${message.author.userName}!`);
});
bot.onDirectMessage(async (thread, message) => {
await thread.post("Hello from X!");
});
When using createXAdapter() without arguments, credentials are auto-detected from environment variables.
X setup
1. Create an X app
- Go to the X developer portal and create a Project and App
- Under Keys and tokens, copy the API Key Secret (consumer secret): this becomes
X_CONSUMER_SECRET - Enable OAuth 2.0 user authentication with the scopes
tweet.read,tweet.write,users.read,dm.read,dm.write,like.write, andoffline.access - Complete the OAuth 2.0 flow for the bot account. Either store the access token as
X_USER_ACCESS_TOKEN, or storeX_CLIENT_IDplusX_REFRESH_TOKENto let the adapter manage token refresh
2. Register a webhook
X delivers events through the X Activity API. Set this up once in the X developer console, which handles the auth for you:
- Register your webhook URL (
https://your-domain.com/api/webhooks/x). It must be public HTTPS without a port. X immediately sends a CRC challenge, which the adapter answers automatically - Create subscriptions for the events the adapter consumes:
post.mention.create,dm.received, anddm.sent(private events, so the bot user must have authorized your app first)
Subscription and webhook management is one-time setup, not adapter runtime. If you script it instead of using the console, the Activity API endpoints are auth-picky and operation-specific and do not fully match the published spec (creating a private-event subscription needed OAuth 1.0a user context in testing, while list and delete used the app-only bearer token), so the console is the simpler path.
3. Environment variables
X_CONSUMER_SECRET=... # App API key secret, used for webhook CRC and signature verification
# Auth option A: static access token
X_USER_ACCESS_TOKEN=... # OAuth 2.0 user-context access token for outbound calls
# Auth option B: managed OAuth refresh (recommended for long-running bots)
X_CLIENT_ID=... # OAuth 2.0 client ID
X_REFRESH_TOKEN=... # OAuth 2.0 refresh token (requires the offline.access scope)
X_CLIENT_SECRET=... # Optional, only for confidential clients
X_ENCRYPTION_KEY=... # Optional, base64 32-byte key to encrypt persisted tokens
X_USER_ID=... # Bot account user ID. Optional if omitted it is fetched from /2/users/me; the adapter requires a resolvable bot id and fails init otherwise
X_USERNAME=... # Optional, bot @handle for mention detection (fetched when omitted)
X_API_BASE_URL=... # Optional, override the X API base URL
Token refresh
X OAuth 2.0 user tokens are short-lived (about two hours). With X_CLIENT_ID and X_REFRESH_TOKEN set, the adapter refreshes the access token before expiry and persists the rotated refresh token in your state adapter, so the bot survives restarts. Set X_ENCRYPTION_KEY to store those tokens AES-256-GCM encrypted.
Alternatively, pass a token provider and plug in your own refresh logic:
import { createXAdapter } from "@chat-adapter/x";
const adapter = createXAdapter({
userAccessToken: async () => refreshTokenFromMyStore(),
});
Webhook setup
X uses two webhook mechanisms, both handled by the adapter:
- CRC challenge (GET): X sends a
crc_tokenthat the adapter answers with an HMAC-SHA256 response keyed by your consumer secret. X re-validates hourly - Event delivery (POST): activity events signed via the
x-twitter-webhooks-signatureheader, verified against the raw request body
// Next.js App Router example
import { bot } from "@/lib/bot";
export async function GET(request: Request) {
return bot.webhooks.x(request);
}
export async function POST(request: Request) {
return bot.webhooks.x(request);
}
Features
Messaging
| Feature | Supported |
|---|---|
| Post message | Yes (mention replies and DMs) |
| Top-level posts | Yes (channel.post on x:public) |
| Edit message | Posts only (X edit eligibility rules apply) |
| Delete message | Posts and own DM events |
| Streaming | Buffered (accumulates then posts once) |
| Typing indicator | No |
Rich content
| Feature | Supported |
|---|---|
| Card format | Plain text fallback |
| Buttons | No (link buttons render as text) |
| Tables | ASCII |
| Modals | No |
| Image uploads | Yes (png, jpeg, webp; up to 4 per post; also DMs) |
Attach images by passing files (or attachments) on the message; the adapter uploads each through X's chunked media endpoints (initialize then append then finalize) and attaches the returned media_ids to the post or DM. A post can carry media with or without text.
await thread.post({
markdown: "France lead the title race",
files: [{ data: pngBuffer, filename: "odds.png", mimeType: "image/png" }],
});
Media upload requires the media.write scope on your OAuth 2.0 token, in addition to tweet.write. Mint the token with media.write included or uploads fail with a 403.
Conversations
| Feature | Supported |
|---|---|
| Mentions | Yes (post.mention.create) |
| DMs | Yes (dm.received / dm.sent) |
| Reactions | Likes only (emoji.heart or "like") |
| User lookup | Yes |
Message history
| Feature | Supported |
|---|---|
| Fetch messages | DMs via API, posts from cache |
| Fetch single message | Posts via API, DMs from cache |
Thread ID format
x:post:{conversationId} # public post threads (channel: x:public)
x:dm:{participantUserId} # direct message with a single user
Examples: x:post:1943467279943467279, x:dm:783214. X DM webhooks carry no conversation id, only participant ids, so DMs are threaded by the other participant's user id: openDM("783214") returns x:dm:783214, and sends route to POST /2/dm_conversations/with/783214/messages. Top-level posts go through channel.post on the x:public channel.
Automation policy
X enforces automation rules. Before deploying a bot:
- get explicit consent before sending automated replies or DMs, and honor opt-outs immediately
- disclose the bot identity in the account profile
- never send bulk, duplicate, or aggressive automated content
- use only the official API (no scraping or browser automation)
The adapter is strict by default: it never streams by post-and-edit, rejects unsupported interactions loudly, and only replies where your handlers decide to.
AI Coding Agents
If you use an AI coding agent such as OpenAI Codex, Claude Code, or Cursor, install the Chat SDK skill so it knows the SDK APIs, adapter patterns, and project conventions before writing code.
npx skills add vercel/chat
The skill references bundled documentation in node_modules/chat/docs, plus adapter guides and starter templates in the published package.
You can also install the Vercel Plugin for a broader agent toolkit: it includes the Chat SDK skill alongside specialist agents, agent slash commands, and more:
npx plugins add vercel/vercel-plugin
The plugin is optional; the skill alone is enough to build with Chat SDK.
For agent-readable documentation, see chat-sdk.dev/llms.txt (page index) or chat-sdk.dev/llms-full.txt (full text).
License
MIT