From 66423cf66b1b6fe93d18f8419b37872fff3e7901 Mon Sep 17 00:00:00 2001 From: Agent Date: Sat, 7 Feb 2026 19:20:12 +0000 Subject: [PATCH] Remove redundant work-detection from HEARTBEAT.md (now in AGENTS.md) --- HEARTBEAT.md | 10 ---------- 1 file changed, 10 deletions(-) diff --git a/HEARTBEAT.md b/HEARTBEAT.md index 497c8ec..7f912bd 100644 --- a/HEARTBEAT.md +++ b/HEARTBEAT.md @@ -10,18 +10,8 @@ Check the following and notify only once per event (track in `memory/heartbeat-s **First nudge at 19:00**: On the first heartbeat at/after 19:00 Vienna, always check in — ask what they're doing if not in active conversation, or nudge toward winding down if already chatting about work/tinkering. - **Active work detection**: If user is chatting with me about work tasks, I KNOW they're working. Don't just passively help — actively look for stopping points. - - **During work conversations after 19:00**: - - Track how long the current task has been going - - When a subtask completes or there's a natural pause, suggest: "This might be a good stopping point for tonight" - - If a task is dragging on (30+ min with no end in sight), gently note: "This is getting complex — want to pick it up tomorrow with fresh eyes?" - - Don't wait for them to ask — proactively identify when a task can be paused - **If NOT in active conversation**: Send a brief WhatsApp asking what they're doing (working? winding down? about to start something new?). Log responses in `memory/wind-down-log.json`. - **If they're about to start something new after 20:00**: Gently suggest postponing to tomorrow. - **Concrete wind-down suggestions**: Don't just say "maybe wind down" — use real data: - `bin/jellyfin resume` → suggest continuing what they're watching - `bin/jellyfin recent` → suggest something newly added