Changed
- Restyled live subagent rendering, async widgets, and background completion notifications with compact Claude-style visual grammar while preserving existing observability paths.
- Parallel subagent result rendering now labels parallel workers as
Agent Ninstead ofStep N, while chain rendering keeps step terminology.
Fixed
/runand single-agent tool calls now allow self-contained agents to run without a task string.- The
subagenttool description no longer advertises hardcoded builtin agent names and management list output now separates disabled builtins from executable agents. - Flexible
subagenttool schema fields now include explicit JSON Schema types so llama.cpp and local OpenAI-compatible providers accept them. - Settings package sources now resolve explicit
git:andnpm:entries from project and user package caches. - Slash-command subagent results are now export-friendly, including completed output and child session paths in visible export content.