AI Docs
Chat & Streaming
Transports
Tools
Middleware
Chat UI Recipes
Interrupts
MCP
Resumable Streams
Persistence
Persistence (Advanced)
Media
Embeddings
Reranking
Evaluate
Code Mode
Computer Use
Harness
- Build your first harness
- Host options
- Send and show media
- Connect clients
- Write a client in any language
- Access and tenants
- Run in the terminal
- Deploy a harness
- Send inputs safely
- Run a tool without a model
- Durable sessions
- Run background work on workers
- List, rename, and fork sessions
- Lifecycle and retention
- Run side effects once
- Wait for a person
- Build on the session log
- Control how a turn ends
- Store settings per thread
- Compact a long session
- Fork and reset a thread
- One log for a session tree
- Write a plugin
- Track usage and cost
- Ask before risky tool calls
- Give your agent coding tools
- Sandbox and extend the coding tools
- Run the coding tools for many threads
- Undo a turn
- Build a coding agent
- Delegate to coding agents
- Switch between agent profiles
- Auth and connectors
- Share a thread between people
- Connect model providers
- Build your own UI
- Code mode in a harness
- Work until a goal is met
- Run agents from a harness
- Hand off a conversation
- Add skills
- Use MCP servers
- Give your agent a computer
- Use from any MCP client
- Use a harness from an editor (ACP)
Sandboxes
- Overview
- Quick Start
- Providers
- Harnesses
- Harness Auth
- Workspace
- Tools
- Policy
- Lifecycle & Snapshots
- Portable Snapshots
- Keep Files After Reload
- Save a Named Version
- Branch From a Version
- Send a Frozen File
- Let the Agent Save and Fork
- Pick Which Files to Keep
- What a Snapshot Stores
- Instance Durability
- Durable Runs
- Events
Sandboxes (Advanced)
Advanced
- Runtime Context
- Bring Your Own Key
- Keep Keys on the Server
- Debug Logging
- Multimodal Content
- Files API
- Per-Model Type Safety
- Runtime Adapter Switching
- Tree-Shaking
- Extend Adapter
- Extend Adapter: Advanced
- Typed Pre-Configured Options
- Test with a Fake Model
- Prompt Caching
- Mid-Conversation Changes
- Approval Flow Processing
AI/LLM: This documentation page is available in plain markdown format at/ai/latest/docs/ui/recipes/basic-chat.md
Chat UI Recipes
A chat box with no tools
This recipe is a chat UI with four components: layout, message, text, and input. It has no tools, no interrupts, and no styles.
For a full TanStack Start app with your own API key, read the Basic Chat tutorial.
Server#
Put OPENAI_API_KEY in your server environment. Then add a POST route at /api/chat:
tsx
import {
chat,
chatParamsFromRequest,
toServerSentEventsResponse,
} from '@tanstack/ai'
import { openaiText } from '@tanstack/ai-openai'
export async function POST(request: Request) {
const { messages, threadId, runId } = await chatParamsFromRequest(request)
const stream = chat({
adapter: openaiText('gpt-6.1-sol'),
messages,
threadId,
runId,
})
return toServerSentEventsResponse(stream)
}Client#
tsx
import { fetchServerSentEvents } from '@tanstack/ai-react'
import { createChatHook } from '@tanstack/ai-react/ui'
const chatOptions = {
connection: fetchServerSentEvents('/api/chat'),
}
const { useAppChat, useChatContext } = createChatHook({
options: chatOptions,
components: {
input: () => {
const chat = useChatContext()
return (
<form
onSubmit={(event) => {
event.preventDefault()
const field = event.currentTarget.elements.namedItem('message')
if (!(field instanceof HTMLInputElement)) return
const text = field.value.trim()
if (!text) return
field.value = ''
void chat.sendMessage(text)
}}
>
<input name="message" />
<button type="submit">Send</button>
</form>
)
},
layout: ({ Messages, Input }) => (
<main>
<Messages />
<Input />
</main>
),
message: ({ message, Parts }) => (
<article data-role={message.role}>
<Parts />
</article>
),
},
partsComponents: {
text: ({ part }) => <p>{part.content}</p>,
fallback: () => null,
},
})
export function ChatScreen() {
const chat = useAppChat({ threadId: 'support-chat' })
return <chat.AppChat />
}Render <ChatScreen /> and type a message. The reply streams into the page.
How it works#
- layout gets Messages, Interrupts, and Input as components. Render them where you want them. This chat has no interrupts, so it leaves Interrupts out.
- message gets one message plus a Parts component. Parts picks a component for each part of that message.
- partsComponents.text renders text parts. fallback catches every part type that you did not register. Here it returns null, so other parts render nothing.
- input reads the chat with useChatContext(). It comes before layout, so TypeScript sees that an input is registered and adds Input to the layout props.
Next#
- A tool that shows raw JSON? Read Make a tool look right.
- Colored code in replies? Read Highlight markdown code.