会话守护

管理 OpenClaw 长会话防爆机制（80%自动归档、自动轮换新会话、低 token 交接）及定时任务安装。用户提到 compacting context、会话过长、自动总结归档、session 轮换、LaunchAgent 定时任务时使用。

防遗忘防卡顿的context管理协议。自动监控水位、分区管理、压缩前存档、压缩后恢复。适用于所有OpenClaw agent和sub-agent。在heartbeat或session启动时触发。

自动监控和显示会话状态信息，包括token消耗、模型信息和功能状态。支持开关控制和自定义显示格式。

AI Agent 大任务防卡死指南。解决 agent 在批量操作中 session transcript 膨胀导致 compaction 超时、agent 卡死的问题。涵盖 session 保护策略、脚本化批处理、断点续传、熔断器、OpenClaw 配置调优和实战案例。

Auto context management - monitors usage and triggers memory transfer at 95% threshold to prevent overflow and ensure session continuity. Trigger on "context...

AI agent safety guardrails for tool calls. Use when (1) you want to validate agent tool calls before execution, (2) building agents that run shell commands, file operations, or API calls, (3) adding a safety layer to any MCP server or agent framework, (4) auditing what your agents are doing. Catches destructive commands, SSRF, SQL injection, path traversal, data exfiltration, prompt injection, and credential leaks. Zero dependencies, under 2ms.