Chat surface
The transcript: messages, streaming markdown, and the indicator shown before
the first token arrives. <Chat> composes these for you; reach for them
directly when you are building your own layout around a thread.
Streaming answer
Markdown streams in token by token as the agent replies.
ChatMessageList picks StreamingTextRenderer for assistant text and keeps
partial markdown (an open code fence, half a list) stable while it grows.
Loading the live demo…
ChatMessageList props
| Prop | Type | Notes |
|---|---|---|
messages | DistriChatMessage[] | Required. From useChat or the chat store. |
rendering | 'rich' | 'minimal' | Expanded tool cards, or compact one-line rows. |
toolRenderers | ToolRendererMap | Your own renderer per tool name. See Human-in-the-loop. |
threadId | string | Enables per-message feedback and trace links. |
enableFeedback | boolean | Let the user vote on assistant messages. |
onShowTrace | (threadId: string) => void | Called when the user opens a trace. |
verbose, debug | boolean | More detail in the transcript, for development. |
StreamingTextRenderer props
| Prop | Type | Notes |
|---|---|---|
text | string | Required. The markdown received so far. |
isStreaming | boolean | Shows the caret and tolerates unfinished markdown. |
className | string |
Thinking indicator
The shimmering placeholder shown while an agent is working, before the first token lands.
Loading the live demo…
ThinkingRenderer props
| Prop | Type | Notes |
|---|---|---|
indicator | StreamingIndicator | Required. 'typing', 'thinking' or 'generating'. |
name | string | The agent's display name. |
avatar | ReactNode | Shown next to the indicator. |
thoughtText | string | Reasoning text to show under the indicator, if the model streams it. |
className | string |