Labsco
openai logo

json-render

✓ Official★ 4,081

by openai · part of openai/plugins

AI chat response rendering guidance — handling UIMessage parts, tool call displays, streaming states, and structured data presentation. Use when building custom chat UIs, rendering tool results, or troubleshooting AI response display issues.

🧩 One of 7 skills in the openai/plugins package — works on its own, and pairs well with its siblings.

This is the playbook your agent receives when the skill activates — you don't need to read it to use the skill, but it's here to audit before installing.

AI Chat Response Rendering

You are an expert in rendering AI SDK v6 chat responses — UIMessage parts, tool call results, streaming states, and structured data display in React applications.

The Problem

When building chat interfaces with AI SDK v6, the raw message format includes multiple part types (text, tool calls, reasoning, images). Without proper rendering, responses appear as raw JSON or malformed output.

AI SDK v6 Message Format

In v6, messages use the UIMessage type with a parts array:

interface UIMessage {
  id: string
  role: 'user' | 'assistant'
  parts: UIMessagePart[]
}

// Part types:
// - { type: 'text', text: string }
// - { type: 'tool-<toolName>', toolCallId: string, state: string, input?: unknown, output?: unknown }
//     state values: 'partial-call' | 'call' | 'output-available' | 'approval-requested' | 'approval-responded' | 'output-denied'
// - { type: 'reasoning', text: string }
// - { type: 'step-start' }  // internal, skip in rendering

The simplest approach is to use AI Elements, which handles all part types automatically:

import { Message } from '@/components/ai-elements/message'
import { Conversation } from '@/components/ai-elements/conversation'

{messages.map((message) => (
  <Message key={message.id} message={message} />
))}

⤳ skill: ai-elements — Full component library for AI interfaces

Manual Rendering Pattern

If you need custom rendering without AI Elements, follow this pattern:

'use client'
import { useChat } from '@ai-sdk/react'
import { DefaultChatTransport } from 'ai'

export function Chat() {
  const { messages, sendMessage, status } = useChat({
    transport: new DefaultChatTransport({ api: '/api/chat' }),
  })

  const isLoading = status === 'streaming' || status === 'submitted'

  return (
    <div>
      {messages.map((message) => (
        <div key={message.id}>
          {message.parts?.map((part, i) => {
            // 1. Text parts — render as formatted text
            if (part.type === 'text' && part.text.trim()) {
              return (
                <div key={i} className={
                  message.role === 'user'
                    ? 'bg-primary text-primary-foreground rounded-lg px-3 py-2'
                    : 'bg-muted rounded-lg px-3 py-2'
                }>
                  {part.text}
                </div>
              )
            }

            // 2. Tool parts — type is "tool-<toolName>"
            if (part.type.startsWith('tool-')) {
              const toolPart = part as {
                type: string
                toolCallId: string
                state: string
                input?: unknown
                output?: unknown
              }
              const toolName = toolPart.type.replace('tool-', '')

              if (toolPart.state === 'output-available' && toolPart.output) {
                return <ToolResultCard key={i} name={toolName} output={toolPart.output} />
              }

              if (toolPart.state === 'output-denied') {
                return (
                  <div key={i} className="text-sm text-muted-foreground">
                    {toolName} was denied
                  </div>
                )
              }

              if (toolPart.state === 'approval-requested') {
                return (
                  <div key={i} className="text-sm text-yellow-500">
                    {toolName} requires approval
                  </div>
                )
              }

              return (
                <div key={i} className="text-sm text-muted-foreground animate-pulse">
                  Running {toolName}...
                </div>
              )
            }

            // 3. Reasoning parts
            if (part.type === 'reasoning') {
              return (
                <details key={i} className="text-xs text-muted-foreground">
                  <summary>Thinking...</summary>
                  <p className="whitespace-pre-wrap">{(part as { text: string }).text}</p>
                </details>
              )
            }

            // 4. Skip unknown types (step-start, etc.)
            return null
          })}
        </div>
      ))}
    </div>
  )
}

Rendering Tool Results as Cards

Instead of dumping raw JSON, render structured tool output as human-readable cards:

function ToolResultCard({ name, output }: { name: string; output: unknown }) {
  const data = output as Record<string, unknown>

  // Pattern: Check for known result shapes and render accordingly
  if (data?.success && data?.issue) {
    const issue = data.issue as { identifier?: string; title?: string }
    return (
      <div className="rounded border border-border bg-card p-2 text-sm">
        <span className="font-medium text-green-400">
          {name === 'createIssue' ? 'Created' : 'Updated'} {issue.identifier}
        </span>
        <p className="text-muted-foreground">{issue.title}</p>
      </div>
    )
  }

  if (data?.items && Array.isArray(data.items)) {
    return (
      <div className="rounded border border-border bg-card p-2 text-sm">
        <p className="font-medium">{data.items.length} results</p>
        {data.items.slice(0, 5).map((item: Record<string, unknown>, i: number) => (
          <p key={i} className="text-muted-foreground">{String(item.name || item.title || item.id)}</p>
        ))}
      </div>
    )
  }

  if (data?.error) {
    return (
      <div className="rounded border border-destructive/30 bg-destructive/10 p-2 text-sm text-destructive">
        {String(data.error)}
      </div>
    )
  }

  // Fallback: simple completion message (not raw JSON)
  return (
    <div className="rounded border border-border bg-card p-2 text-xs text-muted-foreground">
      {name} completed
    </div>
  )
}

Decision Tree

Building a chat UI with AI SDK v6?
  └─ Want pre-built components?
       └─ Yes → Use AI Elements (⤳ skill: ai-elements)
       └─ No → Manual rendering with parts iteration
            └─ Tool results look like JSON?
                 └─ Create ToolResultCard components for each tool's output shape
            └─ Text not rendering?
                 └─ Check part.type === 'text' and use part.text
            └─ Server errors?
                 └─ Check: await convertToModelMessages(), toUIMessageStreamResponse()

Server-Side Message Validation

Use validateUIMessages to validate incoming messages before processing:

import { validateUIMessages, convertToModelMessages, streamText, gateway } from 'ai'

export async function POST(req: Request) {
  const { messages } = await req.json()
  const validatedMessages = validateUIMessages(messages)
  const modelMessages = await convertToModelMessages(validatedMessages)
  // ...
}

Official Documentation