v2026.6.3

NVIDIA/garakv2026.6.3Jun 3, 2026by virattt

AI Summary

Introduces subagent delegation for parallel task execution, adds CLI progress UI, and significantly improves web fetching capabilities with HTML parsing and caching.

Key Highlights

Added `spawn_subagent` for delegating tasks to isolated workers
Added CLI subagent progress UI with status tracking
Improved `web_fetch` with Readability/Turndown, HTTP caching, and fast-model extraction

New Features

Subagent delegation (`spawn_subagent`)
CLI subagent progress UI
Enhanced web fetching with caching and parsing

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