Agent Activity

One lifecycle or hook event on the agent timeline — what fired around a tool call, and whether its checks passed.

Chronological rail of agent steps and checkpoints — what the agent did, in order.

The named human-in-the-loop variant of Confirmation — a titled, described approval card, binary or N-option with scope.

A line-level unified diff inside an agent transcript — what the agent changed, with correct old/new line numbers.

Hierarchical file/folder list for a workspace — code (IDE source tree) or document (produced assets) look.

A Card-shaped, collapsible plan the agent proposes before it starts executing — and the decision the human returns.

A test run summarised inline in the conversation: totals, the failing cases with their assertions, and a per-suite breakdown.

The artifact a tool PRODUCED, presented as the headline — raised surface, no border, children carry the payload. Its header row is title | actions | status, where actions are scoped to the whole artifact (expand, download, open).

In-turn footer reporting the three facts a running turn owes the user: elapsed time, cost, and how to stop it.