quaner1234-cmd/dsh-subagent-watchdog

README excerpt

dsh-subagent-watchdog A DSH plugin that safely recovers native continuable subagents from one high-confidence failure: explicit max-tokens termination. When a native continuable DSH subagent ends because it hit max-tokens , Watchdog automatically continues the same child conversation once, then stops. No loops. Why When you delegate a task to a continuable subagent in DSH and the child runs out of output tokens mid-task, the runtime ends the turn with stopReason: 'max-tokens' , reports the failure to the delegating agent, and stops. The work sits unfinished; the parent has to notice the failure, decide it is recoverable, and manually continue the child. Watchdog does exactly that one recovery — deterministically, at most once — using only official DSH seams. What it does - First max-tokens on a continuable child — Watchdog observes the terminal turn/end { kind: 'max-tokens' } , starts one official durability checkpoint ( sessions.flush ) while the child session is still live, waits for normal settlement and checkpoint resolution, then sends exactly one continuation through the official subagents.followup() seam. The same durable child conversation cold-resumes in a new activation e…

Category