- GPU unit repoint verified live 2026-09-08: .8 rtx3090 probes
llama-chat-api.service (stale llama-server unit read inactive -> false
UNREACHABLE for a healthy process); .110 keeps llama-server.service
(ocu-llm VM), .15 keeps strix-server.service. is-active no longer
swallowed as SSH failure (|| true).
- check_agents: bind pid before the summary f-string so the non-report-only
path (abiba/koonimo) no longer raises UnboundLocalError (line 305 crash).
- abiba key leg: read LITELLM_API_KEY from /root/.pi/agent/env.sh (#735
moved creds out of shared /root/.bashrc); 'abiba NO KEY' gone on healthy
setup.
The no-mistakes document step had auto-updated the .8 systemd unit name
(llama-server -> llama-chat-api.service) in gpu-fleet.prose.md and
infrastructure-control.prose.md. Those contracts are co-gated with another
agent and cannot be amended inside a script-scope task (firstmate decision
2026-09-08, key prose-doc-step-scope); the unit-name doc sync is separate
follow-up work. This restores both files to their origin/master content.
The litellm-self-heal.prose.md agent-health-check v3/env.sh description
update (same document commit) is intentional and kept.
abiba-bot
requested review from mumuni-bot 2026-09-08 21:40:45 +00:00
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
P0-adjacent monitoring fix per firstmate task agent-health-probe-repoint-20260907. Four verified defects fixed: (1) .8 probes wrong systemd unit name (llama-server -> llama-chat-api.service) causing false rtx3090 UNREACHABLE; (2) UnboundLocalError (pid) crashed the abiba leg; (3) abiba key probe path stale after #735 creds separation - now /root/.pi/agent/env.sh; (4) uptime readout measured the wrong value. no-mistakes validation passed (run 01M20FYWJS4E5APMFBT8FTP3GX). Script-only by design; contract prose doc-sync filed as separate follow-up.