Ballmac UI home

Agent 3: runs and traces

AI agent runs with status, time, tokens and cost, filtered and searched, and a trace waterfall for the selected run: model calls, tool calls and retrieval, each span with input, output and error.

State

The normal view. Pick a state to see what the block shows while it loads, is empty or fails.

Open in v0 (opens in a new tab)

Installation

$ pnpm dlx shadcn@latest add @ballmac/agent-3

Usage

Example: agent-3-demo.tsx
import { Agent3 } from "@/components/ballmac/blocks/agent-3/agent-3"

export default function Agent3Demo() {
  return <Agent3 />
}

States

Pass state and the block does the rest: skeletons that match its layout, a clear empty message, an error you can retry, and announcements for screen readers.

  • Loading

    A skeleton table and trace; search and the status filter are disabled.

    state="loading"
  • No runs yet

    Explains that runs and traces appear once agents work; a filter with no matches says so inside the table instead.

    state="empty" (or runs={[]})
  • Could not load

    An alert with Try again (onRetry).

    state="error"

Quality scorecard

8/8

Every applicable check passes

Measured in Chromium 153.0.8010.12 on October 19, 2026, on version 1.0.0, across 5 examples.

How we measure
  • Passed: Accessibility scan

    No serious or critical issues in light and dark, on a phone and a desktop (axe-core 4.13.0, WCAG 2.1 AA and best-practice rules).

  • Passed: Small screens

    No sideways scrolling at 360, 390 or 1280 px wide.

  • Passed: Reduced motion

    Every endless animation stops when the visitor asks for less motion.

  • Passed: Right to left

    Mirrors correctly in Arabic, Hebrew, Persian and Urdu layouts (8% of elements off the mirror, limit 15%).

  • Passed: Clean console

    No console errors or React hydration errors while loading.

  • Passed: Keyboard

    30 tab stops, each showing a visible change when it takes focus. 3 documented keys.

  • Passed: Loading, empty and error

    Ships loading, empty, error states, each with an example.

  • Passed: Automated tests

    Covered by agent-3.test.tsx.

  • For information: Footprint

    4.9 KB of source (gzip) in 1 file. Installs lucide-react.

Automated checks find a subset of problems and do not replace testing with a screen reader and a keyboard in your own app. What they miss.

Dependencies

Use with AI

Agent observability. <Agent3 runs={[{ id, agent, task, status: 'success' | 'error' | 'running', started, duration (ms), tokens, cost, spans: [{ id, name, kind: 'llm' | 'tool' | 'retrieval' | 'step', start (ms from run start), duration (ms), depth, status, tokens, input, output, error }] }]} />. Map OpenTelemetry GenAI spans, Langfuse or AI SDK telemetry onto spans; a failed span is selected first. With the shadcn MCP server set up (guide), ask your agent:

Add the Ballmac UI Agent 3: runs and traces (@ballmac/agent-3) to this project with the shadcn MCP, then use it where it fits.

Use it for

  • Debugging what an agent did and where time and tokens went
  • An admin page of recent agent runs

Not for

  • Watching one run live (use agent-1)
  • General request tracing for web services (use log-stream or a data-table)

Registry JSON: https://ui.ballmac.com/r/agent-3.json

Free to use in personal and commercial projects.

Ballmac UI Pro

Need the whole screen, not one piece?

150 premium blocks (dashboards, settings, calendars, mail, shops, onboarding), a private shadcn registry and Figma tokens. Blocks that show data come with loading, empty and error states built in.

Not ready? Try three Pro blocks free

Leave your email and the blocks appear right here, ready to copy. Yours to use in any project.