@elabs-ai/components-ai

The standard chat input — a PromptInput pre-assembled with attachments, tools and submit.

The SAFE generative-UI path: renders an agent-DESIGNED screen from data — a JSON tree of catalog types validated against the catalog — with the real components; actions reach the host's onAction.

A model-emitted, column-oriented data table rendered as message content.

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

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

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

Auto-stick-to-bottom chat transcript region.

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

The chat workspace's right context rail — sources, produced assets and a root↔detail drill-in.