Chain of Thought

Model reasoning steps. Pro · AI chat and agents › Agents and reasoning

Collapsible reasoning trace: the steps a model took before answering.

Installation

npx valyro-cli@latest login
npx valyro-cli@latest add chain-of-thought

npm install valyro-ui-pro

import 'valyro-ui-pro/styles.css';
import { ChainOfThought } from 'valyro-ui-pro';

Prop	Type	Default
`steps` *	`ThoughtStep[]`		Reasoning steps in order; while streaming, the `active` one is previewed in the collapsed header.
`streaming`	`boolean`	`false`	The model is still reasoning: the header shimmers and the panel opens.
`duration`	`number`		Reasoning time in milliseconds, for the "Thought for 12s" summary.
`open`	`boolean`		Controlled `open`; use with `onOpenChange`.
`defaultOpen`	`boolean`		Default: open while `streaming`.
`onOpenChange`	`(open: boolean) => void`		Called with the new `open` when it changes.
`autoCollapse`	`boolean`	`true`	Collapse when `streaming` turns off, so the answer takes the focus. Default true.
`locale`	`string`		BCP 47 locale for the duration; defaults to the ThemeProvider's.
`labels`	`Partial<ChainOfThoughtLabels>`		Overrides for the built-in English text; keys left out keep their defaults.

Tool Call — Tool call with approval
Agent Plan — Live agent task plan
Agent Trace Timeline — Agent steps as a waterfall: time, tokens, cost, inputs and outputs with secrets redacted
Agent Approval Gate — Agent action approval: risk, diff, explicit consent and a decision log
Memory Panel — What the assistant remembers
AI Chat Window — AI chat window
Chat Message — Messages with streaming output
Message Branches — Message versions and a conversation branch tree
Streaming Text — Smooth token streaming
Markdown Preview — Rendered Markdown
Response Feedback — Answer rating and a rubric for reviewers
Prompt Composer — Prompt field with attachments