chat

function chat<TAdapter, TSchema, TStream, TTools, TInterrupts, TContext, TMiddleware, TAgents>(options): TextActivityResult<TSchema, TStream, TTools>;

Defined in: packages/ai/src/activities/chat/index.ts:6128

Text activity - handles agentic text generation, one-shot text generation, and agentic structured output.

This activity supports four modes:

1. Streaming agentic text: Stream responses with automatic tool execution
2. Streaming one-shot text: Simple streaming request/response without tools
3. Non-streaming text: Returns a ChatResult with the text and every chunk (stream: false)
4. Agentic structured output: Run tools, then return structured data

Type Parameters#

TAdapter#

TAdapter extends AnyTextAdapter

TSchema#

TSchema extends SchemaInput | undefined = undefined

TStream#

TStream extends boolean = boolean

TTools#

TTools extends | readonly ( | Omit<Tool<any, any, any, any>, "execute"> & object & object | ProviderTool<string, TAdapter["~types"]["toolCapabilities"][number]>)[] | undefined = | readonly ( | Omit<Tool<any, any, any, any>, "execute"> & object & object | ProviderTool<string, TAdapter["~types"]["toolCapabilities"][number]>)[] | undefined

TInterrupts#

TInterrupts extends readonly InterruptDefinition<any, any, any, any, any>[] = []

TContext#

TContext = unknown

TMiddleware#

TMiddleware extends unknown[] | undefined = undefined

TAgents#

TAgents extends readonly DefinedAgent<string, readonly SubagentTool[], SchemaInput | undefined, readonly InterruptDefinition<any, any, any, any, any>[], any, unknown, AgentProduces | undefined>[] = readonly DefinedAgent<string, readonly SubagentTool[], SchemaInput | undefined, readonly InterruptDefinition<any, any, any, any, any>[], any, unknown, AgentProduces | undefined>[]

Parameters#

options#

TextActivityOptionsWithContext<TAdapter, TSchema, TStream, TTools, TInterrupts, TContext, TMiddleware, TAgents>

Returns#

TextActivityResult<TSchema, TStream, TTools>

Examples#

Full agentic text (streaming with tools)

import { chat } from '@tanstack/ai'
import { openaiText } from '@tanstack/ai-openai'

for await (const chunk of chat({
  adapter: openaiText('gpt-5.5'),
  messages: [{ role: 'user', content: 'What is the weather?' }],
  threadId,
  tools: [weatherTool]
})) {
  if (chunk.type === 'TEXT_MESSAGE_CONTENT') {
    console.log(chunk.delta)
  }
}

One-shot text (streaming without tools)

for await (const chunk of chat({
  adapter: openaiText('gpt-5.5'),
  messages: [{ role: 'user', content: 'Hello!' }],
  threadId,
})) {
  console.log(chunk)
}

Non-streaming text (stream: false)

const { text, chunks } = await chat({
  adapter: openaiText('gpt-5.5'),
  messages: [{ role: 'user', content: 'Hello!' }],
  threadId,
  stream: false
})
// text is a string with the full response
// chunks is every chunk the run produced, in order

Agentic structured output (tools + structured response)

import { z } from 'zod'

const result = await chat({
  adapter: openaiText('gpt-5.5'),
  messages: [{ role: 'user', content: 'Research and summarize the topic' }],
  threadId,
  tools: [researchTool, analyzeTool],
  outputSchema: z.object({
    summary: z.string(),
    keyPoints: z.array(z.string())
  })
})
// result is { summary: string, keyPoints: string[] }