mirror of
https://github.com/x1xhlol/system-prompts-and-models-of-ai-tools.git
synced 2026-06-18 07:19:35 +00:00
Upgraded from 2026.4.2 to 2026.4.11: Stability & Transport: - Safer provider transport with health checks and auto failover - Connection pooling and graceful degradation Exec Approvals (enhanced): - 3-tier classification: auto_approve, require_approval, forbidden - 11 approval-gated actions, 6 auto-approved, 3 forbidden Subagents: - max_spawn_depth: 2 (orchestrator pattern) - max_concurrent: 8 with session isolation Channels: - WhatsApp: emoji reactions, typing indicator, auto-chunking - Slack: exec approval routing - Matrix: streaming + proxy + history + thread replies - Email: outbound primary Memory: - Active Memory plugin with auto context injection - REM backfill (replay old notes into durable memory) Flows: - Background task flow control plane (SQLite-backed) - Checkpoint on step, resume on restart https://claude.ai/code/session_01LsnvBa7HwF5hs99VZbgLGj |
||
|---|---|---|
| .. | ||
| openclaw-config.yaml | ||