AI and Terminal
Chat, code and console surfaces for working with a model.
What did the agent do, and what is it asking me?
One agent run, reviewable end to end: a Plan with its decision contract, an AgentTimeline whose last step follows your answer, a Tool call with arguments and result one click away, a ToolResultCard hosting the chart the run produced, TokenUsage in the header and an ApprovalCard for the one side effect that waits for a human. Reports the decision through onDecision and never performs it.
Renders a model's chart tool-output inside an AI conversation — AutoChart (@elabs-ai/components-charts) composed with Tool/ToolOutput from @elabs-ai/components-ai. The canonical copy-owned home for @elabs-ai/components-ai + @elabs-ai/components-charts cross-sibling composition.
Multi-file Monaco code editor with brand-ui tabs and token theming (wire @elabs-ai/components-editor/monaco-environment once at the app entry).
A settled coding-agent console: launch banner, transcript, composer with mode/effort indicator, status bar. Nothing is running.
A coding-agent console under way: tool calls, a diff hunk, a working line with a stop affordance, a pending permission prompt, status bar.