feat/add watchdog#2362
Open
SergeiHanus wants to merge 2 commits into
Open
Conversation
…d auto-remediation
Installs a systemd timer (15 min) that detects three failure modes:
- Dead recurring series: status=failed AND recurrence IS NOT NULL
- Stuck processing: status=processing >45 min with stale heartbeat
- Service down: systemctl --user is-active returns non-zero
On detection, invokes claude --dangerously-skip-permissions with a
structured prompt to auto-remediate and inject a task row into inbound.db
so the agent notifies the user via their channel.
Ships:
- scripts/watchdog.ts detection logic (queries agent_groups.name)
- scripts/watchdog-prompt.ts prompt builder + claude invocation
- setup/watchdog.{service,timer} systemd units
- setup/install-watchdog-timer.sh installer
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Type of Change
.claude/skills/<name>/, no source changes)Description
Install the NanoClaw watchdog — a systemd timer that runs every 15 minutes to detect failed/stuck digest sessions and invokes Claude Code to auto-remediate before the user notices messages stopped. Detects three failure modes: dead recurring series (status=failed AND recurrence IS NOT NULL), stuck processing (status=processing >45 min with stale heartbeat), and service down. Use when the user wants proactive failure detection and auto-recovery.
For Skills