dsh-watchdog
DeepSeek Harness 插件：冻结监视器 + 自恢复——心跳检测、过期实例检测、孤立工作进程清理，以及下一会话可据此采取行动的恢复报告。
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add dsh-watchdog@0.1.2Watchdog 以 dsh-watchdog 发布，当前版本为 0.1.2。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
DeepSeek Harness plugin: freeze watchdog + self-recovery — a "pojistka" (insurance) against the harness freezing and never coming back.
~/.dsh/watchdog/heartbeat.json
with the current pid, boot time, and session count.image_worker.py, voice_worker.py, agent_voice_worker.py)
left behind by the frozen instance, and writes a recovery report to
~/.dsh/watchdog/recoveries/.clean: true, so the next boot knows it was not a freeze.dsh_watchdog: status (heartbeat, uptime, sessions, last
recovery), recover (run the recovery routine now), history (list past
recovery reports).If the harness freezes (e.g. a plugin fails at apply time, or a worker hangs),
starting a new session used to fail or leave stale processes behind. With this
plugin, the next session automatically detects the frozen instance, cleans up,
and can continue — the agent is told to check dsh_watchdog status after a
freeze and resume interrupted work.
dsh plugin --profile web add dsh-watchdog
Restart the web profile. The tab appears in the conversation view ring and the
dsh_watchdog tool is available to the agent.
| Field | Default | Meaning |
|---|---|---|
enabled | true | Write the heartbeat at all. |
heartbeatSeconds | 5 | Heartbeat interval. |
staleAfterSeconds | 30 | A heartbeat older than this (with a live pid) means "frozen". |
killStaleWorkers | true | Kill orphaned image/voice/agent-voice workers during recovery. |
~/.dsh/watchdog/
heartbeat.json # current instance liveness
recoveries/recovery-<ts>.json # one report per detected freeze/crash
lib/index.js (heartbeat + recovery + tool).lib/client.js (status tab).npm install # nothing required (peers provided by the harness)
npm publish # publish a new version
MIT