# Shadcn Agent Activity blocks

> Agent run views, from live step feeds and approvals to research traces, MCP call tables, and run reports.

- Type: Pro blocks (AI & Agents)
- Page: https://web.dev.reui.io/blocks/ai-agents/agent-activity
- Blocks: 5
- Installs with a ReUI Pro or Ultimate license; setup: https://web.dev.reui.io/docs/license-setup

## When to use

- A live step feed of one agent run that the person who started it can approve, pause or stop
- The research trail behind an answer: the search query, numbered sources, repo files and confidence
- A record of what a run touched and settled: MCP calls per server, refused scopes and failed items

## When not to use

- Operator pages across many runs: a run queue, an approval inbox or tool access settings: use the [Agents blocks](https://web.dev.reui.io/blocks/solutions/agents.md)
- The conversation around the run: the message thread, the prompt composer and the replies: use the [AI Chat blocks](https://web.dev.reui.io/blocks/ai-agents/ai-chat.md)
- A dated history of what people did, such as activity feeds, milestones or release notes: use the [Timeline blocks](https://web.dev.reui.io/blocks/application/timeline.md)

## Agent notes

- Each page.tsx pads a top aligned `min-h-svh` wrapper around `AgentActivity`, whose root caps at `max-w-xl` or `max-w-2xl`; drop the wrapper in your layout
- Each run is replayed from the block's data file on `setTimeout` timers; drive the same state from your agent's events instead
- Each block calls `toast` from `sonner` but mounts no toaster, so those messages stay hidden until your layout renders one

## Third-party libraries

- Sonner v2: [API reference](https://sonner.emilkowal.ski/toast), [docs](https://sonner.emilkowal.ski/getting-started), used by 5 of 5 blocks

## Blocks

- [Approval Run Console](https://web.dev.reui.io/blocks/ai-agents/agent-activity/agent-activity-1.md): Agent run console that stops at approval steps for an inline Approve, Revise or Deny. Best for a run that stops for a person, flagging High impact approvals in the queue ahead, with Revise notes and a fold for finished steps.
- [Live Run Feed](https://web.dev.reui.io/blocks/ai-agents/agent-activity/agent-activity-2.md): Live agent run feed with Summary, Detailed and Raw monospace log views. Best for a watch and stop feed with no approval gates, headed by the requester's avatar and start time, counting files touched and tools called.
- [Research Timeline](https://web.dev.reui.io/blocks/ai-agents/agent-activity/agent-activity-3.md): Research timeline from search query via cited sources and repo files to a confidence rated answer. Best for a reply's evidence with no run controls: numbered sources with publisher logos, repo files with line counts and a confidence badge.
- [MCP Call Audit](https://web.dev.reui.io/blocks/ai-agents/agent-activity/agent-activity-4.md): MCP call table attributing each tool call to its server, with the refused scope and a Grant. Best for a table of tool calls by server with status dots, a footnote naming servers that received nothing, and rows that stack in a narrow container.
- [Run Outcome Report](https://web.dev.reui.io/blocks/ai-agents/agent-activity/agent-activity-5.md): Agent run outcome report with a done, failed or skipped badge per item and a scoped retry. Best for a settled run's ledger marking unchecked successes Unsupported and rerunning skipped items once their blocker recovers, with Discard.

Every ReUI item has a twin like this one; the index is https://web.dev.reui.io/llms.txt. Agents with the ReUI MCP (https://web.dev.reui.io/docs/mcp) get the same guidance from the getters named above.