llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

The 2026-10-09 wire aliases become the service names everywhere:
systemd units, serve scripts, env files and FRANK_* variables,
deploy-plan/deploy-remote service keys, container names, Prometheus
job names + alert rules, Grafana dashboard queries, bats seams,
runbook filenames, homepage/AGENTS lore, and historical prose.
Rollback tags renamed in lockstep. Residue in the tree: zero.
Retired frank-medium/small/npu names are history and stay.

Known casualty: scripts/patches/*.patch context lines were rewritten;
those retired-era vLLM-fork patches no longer apply byte-exact.
This commit is contained in:
Frank
2026-10-10 17:03:14 -07:00
parent 5ced474eb9
commit 55f87fcdce
195 changed files with 2085 additions and 2064 deletions
+13 -13
View File
@@ -32,7 +32,7 @@ scrape_configs:
# bridge container, and on this netavark host a container can only reach the
# host's LAN IP at a PUBLISHED port — node-exporter's net=host bind on
# 192.168.0.143:9100 is refused by construction (the same rule that sends
# frank-large and frank-secondary to the gateway below). node-dankserver is a
# frank-dragoon and frank-zealot to the gateway below). node-dankserver is a
# different machine, so its LAN address works.
- job_name: "node-dankclaw"
static_configs:
@@ -79,55 +79,55 @@ scrape_configs:
# this container, not the guarded vhosts: these are machine clients and
# Prometheus cannot solve an Anubis challenge.
#
# One metric namespace: llamacpp:* — frank-large, frank-secondary and
# frank-primary, all llama.cpp with /metrics (the family verified from
# One metric namespace: llamacpp:* — frank-dragoon, frank-zealot and
# frank-archon, all llama.cpp with /metrics (the family verified from
# /metrics on 2026-09-16 and 2026-09-20) and all exporting
# requests_deferred (the queue depth, the only form llama.cpp shows the
# capacity wall in), spec_decode_num_drafts_total, tokens_predicted_total,
# and the prompt_tokens_cached_total / prompt_tokens_total reuse pair.
#
# frank-large and frank-secondary are scraped over host.containers.internal,
# frank-dragoon and frank-zealot are scraped over host.containers.internal,
# not their own LAN addresses: this Prometheus is a bridge-networked
# container (Network=dankclaw_default), and on this netavark host a
# container can only reach the host's LAN IP at a PUBLISHED port — a
# host-process bind like llama-server's 0.0.0.0:7770 is refused at
# 192.168.0.143:7770 while it answers at 169.254.1.2:7770. That is
# why frank-secondary was red here for days (up{job="frank-secondary"} == 0,
# why frank-zealot was red here for days (up{job="frank-zealot"} == 0,
# "dial tcp 192.168.0.143:7771") even though the endpoint was healthy and
# exporting: the target address was unreachable by construction, not the
# service down. Same host, same rule, so both local endpoints use the
# gateway.
#
# (2026-10-05) frank-primary LEFT the llamacpp family with FreeToken
# (2026-10-05) frank-archon LEFT the llamacpp family with FreeToken
# (the PR587 ROCm engine then serving it had NO /metrics — the job
# scraped 404s forever, a structural never-green) and RE-JOINED the same
# day on the radiance engine: its exporter speaks vLLM-compatible names
# plus radiance:* families, a different namespace — hence the separate
# job below, not a re-add to the llamacpp pair. The netavark quirk above
# is same-host only; plain LAN routing REACHES 192.168.0.235:7770.
- job_name: "frank-secondary"
- job_name: "frank-zealot"
metrics_path: "/metrics"
static_configs:
- targets: ["host.containers.internal:7771"]
labels:
service: frank-secondary
service: frank-zealot
- job_name: "frank-large"
- job_name: "frank-dragoon"
metrics_path: "/metrics"
static_configs:
- targets: ["host.containers.internal:7770"]
labels:
service: frank-large
service: frank-dragoon
# frank-primary (dankserver) — the radiance engine since 2026-10-05.
# frank-archon (dankserver) — the radiance engine since 2026-10-05.
# A DIFFERENT host, so plain LAN routing is correct here (the
# host.containers.internal trick is same-host only): health answers at
# 192.168.0.235:7770 from this bridge container. Radiance exports
# vLLM-compatible names plus radiance:* families — NOT the llamacpp:*
# namespace, so llm-fleet rules must not be pointed at this target.
- job_name: "frank-primary"
- job_name: "frank-archon"
metrics_path: "/metrics"
static_configs:
- targets: ["192.168.0.235:7770"]
labels:
service: frank-primary
service: frank-archon
+6 -6
View File
@@ -1,8 +1,8 @@
# Alerting and recording rules for the LLM fleet.
#
# One metric namespace: llamacpp:* — frank-secondary and frank-large, both
# One metric namespace: llamacpp:* — frank-zealot and frank-dragoon, both
# llama.cpp with /metrics (the family verified from /metrics on 2026-09-16
# and 2026-09-20). frank-primary LEFT the family 2026-10-05: FreeToken (the
# and 2026-09-20). frank-archon LEFT the family 2026-10-05: FreeToken (the
# PR587 ROCm engine) has no /metrics endpoint, so its scrape job was
# deleted rather than left never-green.
# (The netavark published-port quirk that forces the Dankclaw endpoints
@@ -110,8 +110,8 @@ groups:
annotations:
summary: "{{ $labels.job }}: scrape target down for 2 minutes"
description: >-
Prometheus cannot reach the LLM endpoint. frank-secondary and
frank-large are root units on Dankclaw: `systemctl is-active
frank-secondary` / `frank-large`. Both scraped endpoints export
the llamacpp:* family. (frank-primary left the scrape set
Prometheus cannot reach the LLM endpoint. frank-zealot and
frank-dragoon are root units on Dankclaw: `systemctl is-active
frank-zealot` / `frank-dragoon`. Both scraped endpoints export
the llamacpp:* family. (frank-archon left the scrape set
2026-10-05 — FreeToken exports no /metrics.)