Mercury 1.1.6 pushes terminal agents toward IDE-like daily use
Mercury v1.1.6 focuses on the parts that decide whether a terminal-first personal agent can stay useful all day: more stable TUI startup and input handling, workspace mode that feels closer to an IDE chat, background tasks and sub-agent completion mirroring, session model switching, platform diagnostics, Spotify controls, and a default web-search skill on fresh installs.
ImpactEmerging Sources2 Audienceoperator · developer
The release is less about novelty and more about closing workflow gaps: long tasks need status, coding sessions need navigation, and operators need model/provider visibility without leaving the session.
- Official GitHub release v1.1.6 published 2026-05-06 13:09 UTC
- Release notes list /bg background operations, sub-agent lifecycle mirroring, /code agent delegation, /models commands, and mercury doctor --platform
- NPM package published as @cosmicstack/[email protected] with Node >=20 requirement
- Mercury still needs broader real-world validation compared with larger ecosystems
- Workspace interception and background handoff behavior should be tested against accidental mode switches
- Spotify album-art rendering is explicitly gated to local iTerm sessions