Grok Build ships v1.0.38-40: subagents default to parent model, long-run agent workflows get steadier
XFreeze · x · 2026-09-22
xAI's coding agent tool Grok Build received a string of updates (v1.0.38–1.0.40) aimed at long-running agent workflows:
- Subagents: can now default to general-purpose without specifying a type, use the parent model locked in at session start, and custom agent profiles survive session resumes.
- Stability: images survive multiple compactions more reliably; MCP tools auto-recover from obvious JSON-shape mistakes; model effort levels now come from the API instead of hard-coded lists.
- Quality-of-life: long agent replies in prompt-suggestion transcripts no longer get cut off mid-sentence; pasted images survive yank/undo/history recall; deployments can control readfile behavior for skill and instruction files; cleaner permission prompts; tool calling now sends a leaner inline-only usetool schema.
- Repo hygiene: helper scripts, logs, and PR drafts moved to the system temp directory, plus fixes around worktrees, memory captures, timeouts, and subagent labeling.
More from coding & agent
- Disaster relief team runs OpenClaw multi-agent system across 8 messaging channels — heyneighbor · 2026-09-22
- Auto-Optimizing a Non-LLM to Read Chinese Halves Errors at 1/7 the Cost of DeepSeek — davernow · 2026-09-22
- jev-gc: A Context Garbage Collector for LLM Agents, Built With Claude — Maleficent_College57 · 2026-09-22
- Dev complains openclaw is a permissions nightmare, unsure if setup or the tool — brianmichel · 2026-09-22
- Codex code leak reveals Aeon, OpenAI's rumored persistent agent, launch may be imminent — ChrisGPT · 2026-09-22
- Engineer autonomously trains a Jev-competitive model with an agent swarm for $3.1k in 20 hours — denisyarats · 2026-09-22