v2026.6.3

neuml/txtaiv2026.6.3Jun 3, 2026by virattt

AI Summary

Introduces sub-agent delegation for parallel task execution, adds CLI progress tracking, and improves web fetching with better HTML parsing and caching.

Key Highlights

  • New `spawn_subagent` function for parallel task execution
  • Enhanced CLI subagent progress UI
  • Improved `web_fetch` with Readability/Turndown and HTTP caching

New Features

  • Subagent delegation functionality
  • CLI subagent progress UI
  • Readability/Turndown HTML-to-markdown
  • HTTP caching

Full Release Notes

### Changes

- Add `spawn_subagent` to delegate focused sub-tasks to isolated workers (`general-purpose`, `research`, `analysis`); emit multiple calls in one turn to run independent tasks in parallel
- Add CLI subagent progress UI with per-delegate status, tool-use counts, and rolled-up activity
- Improve `web_fetch` with Readability/Turndown HTML-to-markdown, HTTP caching, and fast-model extraction from fetched pages