From 00cdbbb654d7e3dae1da50d2c365eec95c9d1551 Mon Sep 17 00:00:00 2001 From: zap Date: Thu, 12 Mar 2026 21:39:30 +0000 Subject: [PATCH] docs(agent): add concrete subagent monitoring thresholds --- AGENTS.md | 9 ++++++++- MEMORY.md | 1 + 2 files changed, 9 insertions(+), 1 deletion(-) diff --git a/AGENTS.md b/AGENTS.md index c70b80a..f9e2934 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -192,13 +192,20 @@ Handoff rule: Subagent drift / stuck rule: - if a fresh implementation subagent is no longer making crisp progress, inspect before waiting longer +- monitoring cadence for fresh implementation runs: + - do not routine-poll in the first 5 minutes unless the task is very small or something already looks wrong + - at ~5 minutes, if the run is still active, do one lightweight status check + - at ~10 minutes, if still active, inspect the child session/history once for concrete evidence of edits/tests/commits - treat these as intervention triggers: - the run is still active after a reasonable window for the task and has not updated `WIP.md` - the run is looping on broad reads/re-verification without landing state updates or commits - the completion result is unusable, missing evidence, or obviously unrelated to the assigned pass +- concrete time thresholds: + - narrow/scoped pass (single docs/config/script task): suspiciously long at ~12 minutes, intervene by ~15 minutes unless recent inspection shows crisp progress + - medium implementation pass (like one bounded feature slice): suspiciously long at ~20 minutes, intervene by ~25 minutes unless recent inspection shows crisp progress - when triggered: 1. inspect the subagent session/history once - 2. if meaningful progress is still happening, let it finish + 2. if meaningful progress is still happening, let it finish and re-check in 5-10 minutes instead of hovering 3. otherwise kill the run, verify the workspace directly, finish the pass in the main session, and update `WIP.md` yourself 4. record the behavior in memory if it reveals a repeatable failure mode diff --git a/MEMORY.md b/MEMORY.md index 6277376..f78dac3 100644 --- a/MEMORY.md +++ b/MEMORY.md @@ -42,6 +42,7 @@ - For non-trivial implementation work, treat `WIP.md` as the canonical state file and update it after each completed task/sub-task with status, concrete evidence, and the next recommended action. - If a subagent model choice causes execution/auth issues, prefer retrying implementation work on Codex GPT-5.4. - If a fresh implementation subagent stops making crisp progress, inspect once; if it is looping, not updating `WIP.md`, or returns an unusable result, kill it, verify the workspace directly, and finish the pass in the main session. +- Monitoring cadence for fresh implementation subagents: first routine check at ~5 minutes if still running, inspect history at ~10 minutes, treat ~12/15 minutes as the suspicious/intervene threshold for narrow passes and ~20/25 minutes for medium bounded passes unless recent inspection shows crisp progress. ## Infrastructure notes worth remembering - Full `~/.openclaw` backups upload to MinIO bucket `zap` and are scheduled via OS cron every 6 hours.