- Add error handling for git fetch in Phase 0
- Add error handling for pnpm install and build in Phase 1
- Fix heredoc quoting to allow variable expansion in recovery prompt
- Use time-based health check loop instead of counter-based
- Standardize changelog path to ~/.clawdbot/molt/changelog.md
- Make wake command syntax consistent (--mode now)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add detailed cron job prompts for nightly update and morning report
- Add notify.target field to config.json (use platform user IDs, not usernames)
- Add troubleshooting section for common notification issues
- Document freshness check (30h window) to avoid stale reports
- Explain message tool fallback behavior
After a successful rollback, molt now triggers the clawdbot agent to
diagnose and fix the issue. The agent receives crash logs and context,
attempts common fixes, and reports to the user if manual intervention
is needed.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Molt is a self-healing update system for self-hosted Clawdbot instances.
It handles nightly updates from upstream with automatic rollback if
something breaks.
Key features:
- Pulls from upstream, installs deps, builds, restarts gateway
- Health check with stability window (catches crash loops)
- Automatic rollback to pre-update commit on failure
- Module manifest to define what *you* care about (personalized health checks)
- Changelog generation for morning reports
- Agentic recovery philosophy: capture context, let the AI fix edge cases
Files:
- docs/molt.md: Full PRD with architecture, config schema, and rationale
- scripts/molt.sh: Reference implementation (bash)
This is an RFC seeking feedback on approach and integration strategy.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
