Tool Call

Tool call with approval. Pro · AI chat and agents › Agents and reasoning

One tool invocation by a model: arguments, live status, result or error, and an optional approval step.

Installation

npx valyro-cli@latest login
npx valyro-cli@latest add tool-call

npm install valyro-ui-pro

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

Props

Prop	Type	Default
`name` *	`string`		Tool identifier as the model calls it, e.g. `search_docs`.
`title`	`ReactNode`		Human-readable title. Defaults to `name`.
`icon`	`ReactNode`		Replaces the wrench icon.
`status` *	`'awaiting-approval' \| 'running' \| 'success' \| 'error' \| 'denied'`		Lifecycle stage: sets the status icon and label, the live timer, the error and the approval step.
`args`	`unknown`		Arguments the model passed (JSON-serialisable); shown as formatted JSON.
`result`	`unknown`		Tool output: strings show as text, anything else as formatted JSON.
`renderResult`	`(result: unknown) => ReactNode`		Custom result view, e.g. a weather card or a table.
`error`	`ReactNode`		What went wrong, shown while `status` is `error`.
`onRetry`	`() => void`		Adds Retry to the error.
`startedAt`	`DateInput`		Start time; a running call counts up from it.
`duration`	`number`		Run time in milliseconds, shown once the call has finished.
`onApprove`	`(approval: ToolCallApproval) => void`		Human-in-the-loop: shown with Deny while `status` is `awaiting-approval`.
`onDeny`	`() => void`		Adds a Deny button to the approval step while `status` is `awaiting-approval`.
`approvalPrompt`	`ReactNode`		Replaces the default approval prompt.
`variant`	`'card' \| 'inline'`	`'card'`	`inline` is a compact row for chat transcripts. Default `card`.
`open`	`boolean`		Arguments and result are shown. Default: open while awaiting approval.
`defaultOpen`	`boolean`		Initial `open` when uncontrolled.
`onOpenChange`	`(open: boolean) => void`		Called with the new `open` when it changes.
`locale`	`string`		BCP 47 locale for timings; defaults to the ThemeProvider's.
`labels`	`Partial<ToolCallLabels>`		Overrides for the built-in English text; keys left out keep their defaults.

Related components

Chain of Thought — Model reasoning steps
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

Previous: Chain of Thought · Next: Agent Plan · All AI chat and agents