- Rate limiting during reconnection (429): honor retry-after headers
- Placeholder edit fails silently: fallback to sending as new message
- Both fixes deployed to pi Zulip extension
- Polls GPU sidecars every 15s for temp, VRAM, power, utilization
- Creates responsive HTML dashboard at /root/dashboard/gpu-fleet.html
- Served via nginx at /gpu/ on CT 116
- PM2-managed gpu-monitor server on port 9100
- Tracks Strix Halo llama-server via SSH
- Exposes JSON API at /gpu-data for integrations
Documents lessons from building pi Zulip extension and Hermes Zulip plugin:
1. Queue registration content-type
2. Missing bot_user_id for @mentions
3. Zero stream subscriptions
4. Stale errors never cleared
5. Stuck detection too aggressive
6. Env var name mismatch
7. Poll interval too aggressive
8. A2A port conflict
Also: fixed Hermes adapter to clear stale errors on successful poll
Root cause: abiba-zulip extension had STUCK_THRESHOLD_MS=30min.
After 30min of inactivity (overnight), it reported stuck=True, which
triggered the health monitor to restart it — cycling restarts up to 18.
Permanent fixes:
1. STUCK_THRESHOLD_MS raised 30min → 4 hours in extension index.js
2. PM2 restart counter reset: delete+re-add abiba-zulip (was 18, now 0)
3. pm2-self-heal.sh alert threshold documented at 30 (implementation already)
4. Prose contract updated with historical note and threshold rationale
- Added --no-color flag to all PM2 commands
- Self-process guard: abiba-zulip is READ-ONLY, never restarted
- Corrected column indices (PID=6, restarts=8, status=9)
- Added pm2-self-heal.sh shell script implementation
Monitors whether Abiba Bot responds to @mentions in stream topics.
Self-test: sends a test mention, checks for response within 30s.
Documents 4 known failure modes with remediation rules.
Follows same self-improving pattern as litellm-self-heal.
Maps how OpenProse contracts connect to Gitea, containers, remote
agents, and infrastructure. Documents the access matrix, what works
today, and what gaps remain for full enforcement.
Self-improving contract that generates, validates, and iteratively
improves Hermes platform plugins. Tracks generations in knowledge
graph, learns from past successes and failures, and can update
its own rules as new patterns emerge.
Responsibility contract that checks abiba-zulip and abiba-telegram
every 5 minutes. Restarts stopped/errored processes, escalates if
restart count exceeds 5/hour. Logs to knowledge graph and alerts
owner via Zulip DM.
- litellm-health.prose.md: Verifies admin UI, API docs, OIDC auth, container
health, and aggregate health endpoint. Reusable by any Syslog agent.
- hello-world.prose.md: Simple example contract demonstrating OpenProse
function pattern with parameters, returns, and postconditions.
root
jerome