vh
91bda3c480
The box is physically at Fountain Valley, renamed, renumbered onto 10.251/16, and serving inference again. This lands the repo half of that. Host: hostname ana-ml2 -> fv-ml1, pinned to 10.251.50.54 by a dnsmasq reservation so the address the runbook, DNS and LiteLLM all assume is the address it actually has. Its headscale node is renamed too. The sweep ran from scripts/fv-ml1-rename-sweep.sh, whose allowlist is the reason this diff touches current-state files and not the record. Dated persistent-memory entries, archival-memory and incident notes still say ana-ml2 in 31 and 62 places respectively, because that is what the box was when those things happened. Rewriting them would make the history lie. LiteLLM was the load-bearing piece and needed more than the api_base sed the runbook describes. Twenty api_base entries repointed, but a grep-and-verify pass also caught a LIVE pass_through_endpoints target for the scalar-judge reward route still on the old address -- an api_base-only substitution would have left it dead. Four prose references describing current state were repointed as well; one historical note recording where a hand-test was run is deliberately left pointing at 10.250.50.54. Two facts in the server tables were wrong and are corrected here. The site is Fountain Valley, not Anaheim. And the box has FOUR RTX PRO 6000 Blackwell Max-Q, not two -- verified by nvidia-smi -L and independently by PCI enumeration of four GB202GL devices. That is 391 GB of VRAM rather than 196, which changes what fits on it. DNS: fv-ml1, fv-ml1-bmc and fv-gw added under the fv site via the piggyback approach, scriberr re-homed, and the ana-ml2 records removed. Applied to all three resolvers. The BMC record carries a warning that its 802.1q VLAN tag must stay disabled -- it shipped tagging VLAN 250 into an untagged port, which made it invisible to every network-side diagnostic and is the reason it appeared dead through several cable changes. Verified end to end: summarizer and sec both answer through the Anaheim gateway across the mesh to FV seats on different ports.
dockge
Per-host Dockge — a lightweight web UI for managing the host's docker compose stacks. Runs one instance on every Docker host in the fleet.
Default stacks root is /opt/docker/compose/ (fleet convention).
Hosts where /opt/docker/ isn't writable by the deploying user
override DOCKGE_HOST_STACKS_ROOT in their .env — corviduo-dev
sets it to /home/vh/docker (vh lacks passwordless sudo on the
worldtree-team-managed host; see servers/corviduo-dev/README.md).
Layout
compose.yaml— canonical, same file pushed to every host.env.example— per-host tunables;DOCKGE_HOST_LABEL+DOCKGE_HOST_IPvary
Homepage
Labeled homepage.group=Service Networking so all five Dockge instances
collapse into the toolchain group on the dashboard, each card pointing
at its own host's web UI.
Deploy
cp stacks/dockge/compose.yaml stacks-mirror/<host>/dockge/
scripts/deploy-stack.sh <host> dockge --compose
ssh -t <host> 'cd /opt/docker/compose/dockge && sudo docker compose up -d --force-recreate'
The .env with the correct DOCKGE_HOST_LABEL / DOCKGE_HOST_IP must
exist on the host before the deploy — otherwise the homepage labels will
render with empty substitutions. Initial seed per host:
# ana-docker
ssh -t ana-docker 'sudo tee /opt/docker/compose/dockge/.env > /dev/null <<EOF
DOCKGE_HOST_LABEL=ana-docker
DOCKGE_HOST_IP=10.250.50.70
EOF'
# ana-ml2
ssh -t ana-ml2 'sudo tee /opt/docker/compose/dockge/.env > /dev/null <<EOF
DOCKGE_HOST_LABEL=ana-ml2
DOCKGE_HOST_IP=10.250.50.54
EOF'
# nh3-docker
ssh -t nh3-docker 'sudo tee /opt/docker/compose/dockge/.env > /dev/null <<EOF
DOCKGE_HOST_LABEL=nh3-docker
DOCKGE_HOST_IP=10.100.50.40
EOF'
# esh-docker-vm
ssh -t esh-docker-vm 'sudo tee /opt/docker/compose/dockge/.env > /dev/null <<EOF
DOCKGE_HOST_LABEL=esh-docker-vm
DOCKGE_HOST_IP=10.0.50.45
EOF'
# vm-esh-nas
ssh -t vm-esh-nas 'sudo tee /opt/docker/compose/dockge/.env > /dev/null <<EOF
DOCKGE_HOST_LABEL=vm-esh-nas
DOCKGE_HOST_IP=10.0.50.154
EOF'
Authoritative vs mirror
Per-host .env lives on the server and is gitignored.
compose.yaml is authoritative in stacks/dockge/ and gets promoted
into stacks-mirror/<host>/dockge/ before each deploy.