Skip to main content

​
New features

  • PDF and binary file preview. Binary files now open in a built-in viewer instead of trying to render as text. PDFs get a full reader with paging, zoom, and search. See Tabs.
  • Floating Preview button. When the active tab matches a hook that produces an output artifact (PDF, HTML, SVG, …), a Preview button appears in the top-right of the editor. Click it to open a live-reloading popup that refreshes every time the hook runs. See Live preview.
  • Find bar. Press Cmd/Ctrl+F to open an in-editor find bar scoped to the active tab. Step through matches with Enter / Shift+Enter, and toggle case sensitivity. See Keyboard shortcuts.
  • Image attachments in chat. Drop or paste PNG / JPEG / GIF / WebP images into the chat panel to send them to the agent alongside your message. Useful for sharing screenshots, figures, or reference images. See Steering the agent.
  • Drag files in from Finder. Drag files from your filesystem onto the file tree (into any folder) or onto the tab bar to copy them into the workspace and open them. See Tabs.
  • Session viewer. A new viewer lets you replay an agent session end-to-end — tool calls, intermediate messages, and edits — to see exactly what the agent did. See Observability.

​
Updates

  • Outline pane lists pending edits and comments across all tabs. The outline now surfaces every tab with a pending review round or unseen comment, and clicking an item jumps you straight to that tab and location. See Reviewing edits and Comments.
  • Pending tabs float next to the active tab. Tabs with pending agent edits are pulled to sit immediately after the active tab so they stay visible without scrolling the tab bar.
  • Accept feedback in the editor. Accepting an agent edit now flashes a soft halo on the accepted text for a moment, so it’s clear what just landed.
  • Agent plan modal renders markdown. Plans the agent proposes now render with bullets, numbered steps, headings, bold, and inline code instead of as a wall of plaintext. See Delegating tasks.
  • Sign in with a Claude Code OAuth token. DocWriter now also accepts CLAUDE_CODE_OAUTH_TOKEN as a credential source, alongside ANTHROPIC_API_KEY, --api-key, and claude login. See Install.

​
Bug fixes

  • The agent’s Read tool no longer tries to read binary images as text and instead returns a clear error explaining how to attach the image via the chat panel.
  • Various stability fixes across the editor and chat panel.