Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Task continuity, session snapshots, and gateway restart recovery. Use when starting long-running tasks (register them), after gateway restart (check for inte...
Task continuity, session snapshots, and gateway restart recovery. Use when starting long-running tasks (register them), after gateway restart (check for inte...
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
会话状态管理、任务持久化和网关重启恢复。
触发条件动作网关刚重启运行 check-restart,汇报恢复状态开始长时间任务用 task_manager.py add 注册任务用户问"有没有未完成的任务"运行 task_manager.py list任务完成运行 task_manager.py complete任务被中断运行 task_manager.py recover
所有脚本中的 {baseDir} = 本技能的目录路径(SKILL.md 所在目录)。 工作区路径从环境变量 OPENCLAW_WORKSPACE 读取,默认 /workspace。
python3 {baseDir}/scripts/main.py --mode check-restart --workspace /workspace
python3 {baseDir}/scripts/task_manager.py --action list --workspace /workspace
python3 {baseDir}/scripts/task_manager.py \ --action add \ --task-id "task_$(date +%s)" \ --task-type "file_processing" \ --description "处理大量文件" \ --priority normal \ --workspace /workspace
python3 {baseDir}/scripts/task_manager.py \ --action complete \ --task-id <task_id> \ --workspace /workspace
python3 {baseDir}/scripts/task_manager.py \ --action recover \ --workspace /workspace
python3 {baseDir}/scripts/task_manager.py --action status --workspace /workspace
python3 {baseDir}/scripts/session_snapshot.py \ --workspace /workspace \ --action list
python3 {baseDir}/scripts/main.py --mode status --workspace /workspace
当 heartbeat 或用户提到"网关重启"时,执行: python3 {baseDir}/scripts/main.py --mode check-restart --workspace /workspace 解析输出中的 active_tasks 和 recovered_tasks 向用户汇报:哪些任务被恢复、哪些需要手动继续
/workspace/ tasks/ task_queue.json # 任务队列 completed/ # 已完成任务 failed/ # 失败任务 memory/ session_snapshots/ # 会话快照 persistence/ active_tasks.json # 持久化任务 gateway_state.json # 网关状态
脚本使用标准库,无需额外安装依赖 所有数据持久化在 workspace 目录下,重启后不会丢失 task_manager.py 是统一入口,推荐优先使用 gateway_monitor.py 的后台监控模式(full mode)在沙箱中不适用,用 check-restart 代替
Agent frameworks, memory systems, reasoning layers, and model-native orchestration.
Largest current source with strong distribution and engagement signals.