X Freeze

X Freeze

@xfreeze · Twitter ·

Grok Build just got a bit updated with new improvements, features, and bug fixes Release Notes: v0.2.52 Features: • Agent sessions can now respect client auto-approve settings for tools. • ER diagrams now render properly in the TUI instead of showing raw source. • Team logins can now receive centrally-managed config and requirements files. • More built-in skills for document and media work are now available in sandbox sessions. Bug Fixes: • MCP server connections no longer flood reconnects on transient stream errors. • ZDR and team flags are now correctly set right after login instead of later. • Mermaid class and ER diagrams now render correctly with cardinalities and on dark themes. • Fixed silent paste failures (Ctrl+V) on pure-Wayland sessions using wl-paste fallback. • Modals no longer panic with index-out-of-bounds on terminals narrower than their min width. • Mermaid diagram PNGs now correctly render CJK and other non-Latin text. • WezTerm users now see a startup warning and /terminal-setup instructions when Shift+Enter cannot insert newlines. • Ctrl+C cancels now complete in <50 ms instead of blocking up to 2 s. • Repeated varied edit failures on one file no longer trigger doom-loop warnings or terminations.

X Freeze

X Freeze

Grok Build just got a major update with a ton of new features and improvements Release Notes: v0.2.51 Breaking Changes: • grok mcp add now accepts positional arguments (e.g. grok mcp add filesystem -- npx ...), supports --scope project, and adds -e/-H flags for env/headers. Features: • Mermaid flowcharts now render subgraph blocks as titled frames with correct internal and cross-boundary edges. • Class diagrams in Mermaid now render as proper UML boxes with attributes, methods and inheritance arrows instead of raw source. • Permission prompts now accept a double-click on an option to submit it, matching the existing Enter and number-key shortcuts. • New /code-review slash command now ships with the CLI and is always available Bug Fixes: • Plan mode exit reminders no longer appear after the model has already started implementing the plan. • Expanded thinking blocks in scrollback now remain expanded when the agent finishes them. • grok update no longer downloads the same binary twice when multiple updaters or leader checks run concurrently. • Background task IDs after /compact are now shown verbatim so the model can reference them correctly in later tool calls. • Typing / while scrollback is focused now focuses the prompt and opens the slash-command dropdown.

Quoted post media
Post media