--- title: Streaming description: Stream real-time text responses from AI models and other async sources to chat platforms. type: guide prerequisites: - /docs/usage --- # Streaming Chat SDK accepts any `AsyncIterable` as a message, enabling real-time streaming of AI responses and other incremental content to chat platforms. For platforms with native streaming support (Slack), you can also stream structured `StreamChunk` objects for rich content like task progress cards and plan updates. ## AI SDK integration Pass an AI SDK `fullStream` or `textStream` directly to `thread.post()`: ```typescript title="lib/bot.ts" lineNumbers import { ToolLoopAgent } from "ai"; const agent = new ToolLoopAgent({ model: "anthropic/claude-4.5-sonnet", instructions: "You are a helpful assistant.", }); bot.onNewMention(async (thread, message) => { const result = await agent.stream({ prompt: message.text }); await thread.post(result.fullStream); }); ``` ### Why `fullStream` over `textStream`? When AI SDK agents make tool calls between text steps, `textStream` concatenates all text without separators — `"hello.how are you?"` instead of `"hello.\n\nhow are you?"`. The `fullStream` contains explicit `finish-step` events that Chat SDK uses to inject paragraph breaks between steps automatically. Both stream types are auto-detected: ```typescript // Recommended: fullStream preserves step boundaries await thread.post(result.fullStream); // Also works: textStream for single-step generation await thread.post(result.textStream); ``` ## Custom streams Any async iterable works: ```typescript title="lib/bot.ts" lineNumbers const stream = (async function* () { yield "Processing"; yield "..."; yield " done!"; })(); await thread.post(stream); ``` ## Platform behavior | Platform | Method | Description | | ----------- | -------------------- | ------------------------------------------------------- | | Slack | Native streaming API | Uses Slack's `chatStream` for smooth, real-time updates | | Teams | Post + Edit | Posts a message then edits it as chunks arrive | | Google Chat | Post + Edit | Posts a message then edits it as chunks arrive | | Discord | Post + Edit | Posts a message then edits it as chunks arrive | The post+edit fallback throttles edits to avoid rate limits. Configure the update interval when creating your `Chat` instance: ```typescript title="lib/bot.ts" lineNumbers const bot = new Chat({ // ... streamingUpdateIntervalMs: 500, // Default: 500ms }); ``` ### Disabling the placeholder message By default, post+edit adapters send an initial `"..."` placeholder message before the first chunk arrives. You can disable this to wait for real content before posting: ```typescript title="lib/bot.ts" lineNumbers const bot = new Chat({ // ... fallbackStreamingPlaceholderText: null, }); ``` You can also customize the placeholder text: ```typescript title="lib/bot.ts" const bot = new Chat({ // ... fallbackStreamingPlaceholderText: "Thinking...", }); ``` ## Markdown healing During streaming, chunks often arrive mid-word or mid-syntax — for example, `**bold` before the closing `**` arrives. The SDK automatically heals incomplete markdown in intermediate renders using [remend](https://www.npmjs.com/package/remend), so messages always display with correct formatting while streaming. The final message uses the raw accumulated text without healing, so the original markdown is preserved. ## Table buffering When streaming content that contains GFM tables (e.g. from an LLM), the SDK automatically buffers potential table headers until a separator line (`|---|---|`) confirms them. This prevents tables from briefly flashing as raw pipe-delimited text before the table structure is complete. This happens transparently — no configuration needed. ## Structured streaming chunks (Slack only) For Slack's native streaming API, you can yield `StreamChunk` objects alongside plain text for rich content: ```typescript title="lib/bot.ts" lineNumbers import type { StreamChunk } from "chat"; const stream = (async function* () { yield { type: "markdown_text", text: "Searching..." } satisfies StreamChunk; yield { type: "task_update", id: "search-1", title: "Searching documents", status: "in_progress", } satisfies StreamChunk; // ... do work ... yield { type: "task_update", id: "search-1", title: "Searching documents", status: "complete", output: "Found 3 results", } satisfies StreamChunk; yield { type: "markdown_text", text: "Here are your results..." } satisfies StreamChunk; })(); await thread.post(stream); ``` ### Chunk types | Type | Fields | Description | | --------------- | ---------------------------------- | ------------------------------------------------------------------------ | | `markdown_text` | `text` | Streamed text content | | `task_update` | `id`, `title`, `status`, `output?` | Tool/step progress cards (`pending`, `in_progress`, `complete`, `error`) | | `plan_update` | `title` | Plan title updates | ### Task display mode Control how `task_update` chunks render in Slack by passing `taskDisplayMode` in stream options: ```typescript await thread.stream(stream, { taskDisplayMode: "plan", // Group all tasks into a single plan block }); ``` | Mode | Description | | ------------ | ------------------------------------------------------ | | `"timeline"` | Individual task cards shown inline with text (default) | | `"plan"` | All tasks grouped into a single plan block | Adapters without structured chunk support extract text from `markdown_text` chunks and ignore other types. ## Stop blocks (Slack only) When streaming in Slack, you can attach Block Kit elements to the final message using `stopBlocks`. This is useful for adding action buttons after a streamed response completes: ```typescript title="lib/bot.ts" lineNumbers await thread.stream(textStream, { stopBlocks: [ { type: "actions", elements: [{ type: "button", text: { type: "plain_text", text: "Retry" }, action_id: "retry", }], }, ], }); ``` ## Streaming with conversation history Combine message history with streaming for multi-turn AI conversations. Use [`toAiMessages()`](/docs/api/to-ai-messages) to convert chat messages into the `{ role, content }` format expected by AI SDKs: ```typescript title="lib/bot.ts" lineNumbers import { toAiMessages } from "chat"; bot.onSubscribedMessage(async (thread, message) => { // Fetch recent messages for context const result = await thread.adapter.fetchMessages(thread.id, { limit: 20 }); const history = await toAiMessages(result.messages); const response = await agent.stream({ prompt: history }); await thread.post(response.fullStream); }); ``` See the [`toAiMessages` API reference](/docs/api/to-ai-messages) for all options including `includeNames`, `transformMessage`, and attachment handling.