Files
the-nexus/fleet/allegro/allegro-wake-checklist.md
Allegro (Burn Mode) e4b1a197be
Some checks are pending
CI / validate (pull_request) Waiting to run
infra: Allegro self-improvement operational files
Creates the foundational state-tracking and validation infrastructure
for Epic #842 (Allegro Self-Improvement).

Files added:
- allegro-wake-checklist.md — real state check on every wakeup
- allegro-lane.md — lane boundaries and empty-lane protocol
- allegro-cycle-state.json — crash recovery and multi-cycle tracking
- allegro-hands-off-registry.json — 24-hour locks on STOPPED/FINE entities
- allegro-failure-log.md — verbal reflection on failures
- allegro-handoff-template.md — validated deliverables and context handoffs
- burn-mode-validator.py — end-of-cycle scoring script (6 criteria)

Sub-issues created: #843 #844 #845 #846 #847 #848 #849 #850
2026-04-05 21:20:40 +00:00

1.5 KiB

Allegro Wake Checklist

Milestone 0: Real State Check on Wake

Check each box before choosing work. Do not skip. Do not fake it.


1. Read Last Cycle Report

  • Open ~/.hermes/burn-logs/allegro.log
  • Read the last 10 lines
  • Note: complete / crashed / aborted / blocked

2. Read Cycle State File

  • Open ~/.hermes/allegro-cycle-state.json
  • If status is in_progress, resume or abort before starting new work.
  • If status is crashed, assess partial work and roll forward or revert.

3. Read Hands-Off Registry

  • Open ~/.hermes/allegro-hands-off-registry.json
  • Verify no locked entities are in your work queue.

4. Check Gitea for Allegro Work

  • Query open issues assigned to allegro
  • Query open PRs in repos Allegro owns
  • Note highest-leverage item

5. Check Infrastructure Alerts

  • Nostr relay (nostr-relay service status)
  • Evennia MUD (telnet 4000, web 4001)
  • Gitea health (localhost:3000)
  • Disk / cert / backup status

6. Check Lazarus Pit

  • Any downed agents needing recovery?
  • Any fallback inference paths degraded?

7. Choose Work

  • Pick the ONE thing that unblocks the most downstream work.
  • Update allegro-cycle-state.json with target and status: in_progress.

Log Format

After completing the checklist, append to ~/.hermes/burn-logs/allegro.log:

[YYYY-MM-DD HH:MM UTC] WAKE — State check complete.
  Last cycle: [complete|crashed|aborted]
  Current target: [issue/PR/service]
  Status: in_progress