Grok Build 0.2.111 adds one-hour shell commands and more reliable MCP tools
mark_k · x · 2026-07-24
Grok Build 0.2.111 adds a long list of agent workflow and reliability fixes
The release lets users disable image and video generation tools through config or environment variables, exposes session/account details in /session-info, and allows grok doctor fix to run directly inside the TUI.
It also improves day-to-day agent use:
- shell commands can now run for up to one hour
- Grok stops turns that keep repeating the same tool call
- managed MCP tools are less likely to time out on slow operations
- queued prompt edits and combine mode are more reliable
- fixes land for session forking, rewinds, permissions, and concurrent sessions
- Escape now cancels the current agent turn
- macOS voice dictation uses less memory
Related event: Grok Build Update Enhances Developer Tools and Stability(2 posts)→
More from coding & agent
- Codex Voice feels magical, but testers say the best setup is to hand work to stronger CLI models — jacob_posel · 2026-07-24
- Google’s one-hour agentic engineering class covers memory, MCP, and multi-agent systems — HeyAmit_ · 2026-07-24
- Graph engineering gives Claude Code a more scalable workflow — blaizedsouza · 2026-07-24
- A Codex workflow uses the browser to run Deep Research across ChatGPT, Claude, and Gemini — JeremyNguyenPhD · 2026-07-24
- AI agents need five layers, not just prompt engineering — blaizedsouza · 2026-07-24
- Builder rebuilds a Claude Code software factory around planning, implementation, review — blaizedsouza · 2026-07-24