Reporting a post-update behavior for tracking purposes.
**Before 2026.4.15: **WhatsApp 408 disconnect during an active agent run caused a full gateway crash:
Unhandled promise rejection: Error: Agent listener invoked outside active run
**After 2026.4.15: **No crash. Instead, the gateway silently freezes mid-session — no ws ⇄ res activity for ~9 minutes — then paradoxically recovers after a WhatsApp 408 disconnect triggers the health monitor restart.
Log sequence:
23:19:40 [ws] ⇄ res ✓ node.list ← last normal response ← 9 minutes of silence, no ws ⇄ res, webchat and WhatsApp unresponsive 23:28:30 [whatsapp] Web connection closed (status 408) 23:28:30 [health-monitor] restarting (reason: disconnected) 23:28:42 [whatsapp] Listening for personal WhatsApp inbound messages. 23:29:21 [whatsapp] Inbound message ← fully recovered
Setup: Windows 10, OpenClaw 2026.4.15, WhatsApp Desktop, model: openai-codex/gpt-5.4 via ChatGPT OAuth, gateway on loopback port 18789.
The 408 + health monitor restart seems to have acted as an unintentional recovery mechanism. Posting in case it helps confirm whether the fix is complete or if the silent freeze is a separate remaining issue.