Grok Build v1.0.48 adds better control over complex agent runs and parallel tool calls
XFreeze · x · 2026-10-02
Grok Build shipped two updates (v1.0.47 and v1.0.48) aimed at making complex agent runs more predictable:
- /rewind now only lists prompts the user actually typed, skipping automatic runtime turns
- Cancelling one tool call no longer kills unrelated commands running in parallel
- WebSearch and WebFetch properly respect Ask rules, and auth recovery now requires a manual resend instead of auto-retrying refused prompts
- File tools (readfile, searchreplace, grep) handle large, special, and binary files more reliably
- v1.0.47 fixed model-list/context-window desync when switching models and the Goal panel not opening during running workflows
The overall theme: fewer things happening behind the user's back, more deterministic parallel execution.
Related event: xAI's Grok Build ships three updates focused on reliability and performance(3 posts)→
More from coding & agent
- Generic API-catalog MCP server vs one tool per job: a context-bloat experiment — MandeepKaur9407 · 2026-11-16
- Berkeley paper: LLMs answer with stale values even when the update is in context — ombre-ai · 2026-11-16
- Effective HTML: 4.2k-star agent skills turn wireframes into self-contained interactive prototypes — tom_doerr · 2026-11-16
- skills-gate: one gate skill fronts 148 agent skills at just 389 tokens — Distinct-Pie2389 · 2026-11-16
- Open-weight Karpo-Decision-31B tops Decision Index at 73.9, one forward pass per answer — CodeByPoonam · 2026-11-16
- shadcn boosts @uisdk: one-shot UI rebuild that's instantly E2E-testable by AI — shadcn · 2026-11-16