Reasoning

A React component in Beamline's AI & agents category.

The agent's trace, fed by your stream: a shimmering label and the seconds so far while it works, then "Thought for N seconds"; steps that check off, prose thoughts, search sources or tool calls, open while running and folded when done.

Use it for

  • Showing what an agent did while thinking: steps, searches, code, collapsible afterwards.

Not for

  • The answer itself (response).
  • Tool calls with inputs and outputs to inspect (tool-call).
  • A plan that needs approval (plan).

Anatomy

  • header button: glyph, label (shimmer while running), seconds, chevron
  • trace (ordered list with a guide line)
  • query row (search)
  • rows: step check or spinner / source glyph and link / prose / tool with +/− lines
  • +N more
  • polite announcement when a run finishes

Variants

  • variant: steps, reasoning, search, coding

States

  • running (open, shimmer, elapsed seconds)
  • done (folded, "Thought for N seconds" or doneLabel)
  • opened or closed by the person (kept until a new run)
  • controlled (open / onOpenChange)

Keyboard

  • Enter/Space on the header toggles the trace (aria-expanded)
  • Closed traces are out of the Tab order
  • Search rows are links

Motion

The label shimmers while running (still under reduced motion); the trace opens on --motion-in and folds on --motion-out (disclosure-panel); a step that arrives while it runs grows to its height (enter-grow, --duration-morph) and rises in once (enter-rise), so the content below glides; the label eases to each new width (useWidthMorph) so the chevron glides instead of jumping.

Props

PropTypeDefaultDescription
rows (required)ReasoningRow[]—{ id?, primary, secondary?, mono?, add?, del?, href? }
variant"steps" | "reasoning" | "search" | "coding"—
status"running" | "done"—
activeLabel / doneLabel / startedAtstring / string / number—
query / more / iconstring / number / ReactNode—
open / defaultOpen / onOpenChangeboolean—
style / refCSSProperties / native Ref—
classNamesReasoningClassNames—

Built from

Dependencies

lucide-react

Import

import { Reasoning } from "@/components/reasoning/reasoning";

Get it

Reasoning is part of Beamline: 190 React components and screens your coding agent (Claude Code, Codex, Cursor or any MCP client) installs into your app through Beamline's MCP server, as a ready-built package or as plain React source you can change. $49 one payment (regular $200), no subscription, a year of updates, one licence for your whole team. Get Beamline · Connect your agent

More in AI & agents

  • Approval card: The agent stops and asks before it acts: what it wants to do, exactly what that changes, any choices it needs, and Approve or Reject; both run your…
  • Attachment: A file tile: preview or typed glyph with the type named, name, size, upload progress, error with retry, and a keyboard-reachable remove.
  • Chat thread: People talking to people: messages grouped by person and day, reactions, delivery and read receipts that glide to the newest message read, who is typing…
  • Citations: Inline numbered citations that preview their source on hover or focus, plus a numbered source list; streamed answers flow in at an even pace with the…
  • Context cards: The knowledge an agent retrieved before it answered: one card per chunk with what it is about, the text it read with the search words marked, how…
  • Conversation: The scrolling column of a conversation: follows new content while you are at the bottom, stops when you scroll up to read, and offers a way back; shared…
  • Flowchart: A workflow as steps on a dotted canvas: a trigger, conditions that branch into paths side by side, actions and waits, read top to bottom; during a run…
  • Image generation: The frame an AI image is generated into: a field of brand-hued pixels breathes with the progress while the model works, then the image arrives —…
  • Message: One turn in a conversation with an agent: the person's words in a quiet bubble, the agent's answer on the page with its orb mark, trace, tool calls and…
  • Plan: An agent's plan: numbered steps with live status, progress, and Approve / Edit / Reject when it needs sign-off; approving shows progress, and a refusal…
  • Prompt bar: The agent composer: a field that grows, @ to add a source, / for a command, a model picker, files and dictation, and one button that sends with progress…
  • Recommendation card: One suggestion from the agent that the person may take or leave: what it suggests, why, the expected effect and how sure it is (a meter and a word…
  • Response: An assistant's answer as streamed markdown in the system's reading type: bursty tokens flow in at an even pace, each new word fades in through a short…
  • Selection actions: Select a passage and hand it to the agent: a bar over the selection with quick actions, your own instruction and More; while the agent works it says so…
  • Task rows: Background work an agent is doing, one row per task: status as a glyph and a word, what it produced, how long it has run or took, a progress bar while…
  • Tool call: One tool call in an agent's run: status, what it did and a short result on one quiet row that opens to the exact input and output; stops for permission…