release(v4.14.0): multi-agent-mux-reset skill purges and recreates resident agents; registrations refuse during a reset; lsof holders in purge hints; codex purges its capability dir (Issue #78) - archive the review reports, bump the lockstep version

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VCgu9Fa9iT7TbJUSzdq4Ff

README.md

@@ -2,7 +2,7 @@
 
 A **Multi-Agent Orchestration & Messaging Backplane** built on [herdr](https://herdr.dev) and MQTT. It runs long-lived coding agents (`claude`, `agy`, `hermes`, `grok`, `opencode`, `codex`) in isolated herdr panes, delegates work to them as tracked jobs, and drives planner / creator / reviewer loops until every reviewer passes the change.
 
-[![Version: v4.13.0](https://img.shields.io/badge/version-v4.13.0-blue.svg)](VERSIONS.md)
+[![Version: v4.14.0](https://img.shields.io/badge/version-v4.14.0-blue.svg)](VERSIONS.md)
 
 ---