assistant-ui

Chat page for an Eve agent, rendering the session through an assistant-ui thread.

A thumbs-down that asks why, so the signal arrives with a reason attached.

Display file parts with icon, name, size, and a download button.

Everything a run touched, as a tree, with the churn spelled out per file.

Work as a graph rather than a list: branches that fan out and rejoin.

Prompt pills that stagger in after a reply and invite the next turn.

Prompt chips rendered from runtime generated follow up suggestions.

Styled component library for rendering generative UI output.

Theme variables and vocabulary CSS for generative UI output.

A refusal in its own shape, with the nearest thing it can do instead.

Control passing between agents, with the reason and what came along.

Activity heat map with month and weekday labels.

Display image parts with preview, loading states, and a fullscreen dialog.

A dot grid holds the frame while the image resolves out of a blur.

Numbered references inside a sentence, each with a hover preview of its source.

The floating entry point, and the panel it opens into.

A pixel matrix that keeps time while the model has nothing to show yet.

Model provider logos as inline SVG components.

Work measured in minutes: weighted stages, an ETA, and a way out.

A location answer: pins, a route between them, and the list they came from.

Render assistant markdown with headings, lists, links, and code blocks.

Rendered expressions with the working shown, one step at a time.

Dialog listing MCP connectors and custom servers, with OAuth and bearer auth controls.

What it now remembers about you, written during the turn and removable.

The props-driven Mermaid renderer: zoom overlay, skeleton, and error fallback, no runtime required.

Render Mermaid diagrams in messages, including while they stream.

Copy, rate, and regenerate. Each action confirms itself with a small state change.

Navigate between regenerated versions of the same answer without losing your place.

A user bubble and a streaming assistant reply, with actions that appear on hover.

Turns you typed while a run was in flight, stacked and cancelable until it finishes.

Badge with streaming stats: time to first token, total time, and tokens per second.

The bottom sheet: keyboard-aware, quick actions above, thumb-sized targets.

The full list rather than the rail: grouped by family, priced, with what each one can do.

The props-driven model picker: search, groups, and reasoning effort levels, no runtime required.

Model picker with reasoning effort levels, search, and runtime integration.

Animated number that rolls its digits odometer style when the value changes.

Digits that roll into place as a count updates in real time.

First run: three moves that teach what this assistant is actually for.

Calls that went out together, collapsed to one row until you want the detail.

Granting a capability rather than approving one action, with the reach spelled out.

Prompts you saved, searchable, with their variables shown before you insert one.

How much is left, when it comes back, and the way to get more.

Select and quote message text with a floating toolbar and a composer preview.

Select a phrase in an answer and a toolbar offers to quote, explain, or rewrite it.

An answer played back, the spoken word lit as it goes, speed under your thumb.

Collapsible panel for assistant reasoning and thinking content.

How hard to think, and how much of that budget the run actually spent.

A collapsible trace that streams reasoning steps along a timeline, then settles into a summary.