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
+113
-113
@@ -90,12 +90,12 @@ service_is_allowed() {
|
||||
dankclaw:authentik-postgres|dankclaw:authentik-server|\
|
||||
dankclaw:authentik-worker|dankclaw:authentik-outpost|dankclaw:authentik-outpost-ldap|dankclaw:anubis|\
|
||||
dankclaw:caddy|dankclaw:homepage|dankclaw:seerr|dankclaw:marreta|\
|
||||
dankclaw:frank-large|dankclaw:frank-secondary|\
|
||||
dankclaw:frank-dragoon|dankclaw:frank-zealot|\
|
||||
dankserver:romm-mariadb|dankserver:romm-redis|dankserver:romm|\
|
||||
dankserver:copyparty|dankserver:jellyfin|dankserver:calibre-web|dankserver:calibre-server|dankserver:plex|dankserver:tautulli|\
|
||||
dankserver:prowlarr|dankserver:qbittorrent|dankserver:radarr|\
|
||||
dankserver:sonarr|dankserver:lidarr|dankserver:readarr|\
|
||||
dankserver:frank-primary|dankserver:node-exporter|\
|
||||
dankserver:frank-archon|dankserver:node-exporter|\
|
||||
frankbook-pro:gluetun|frankbook-pro:qbittorrent|frankbook-pro:prowlarr|\
|
||||
frankbook-pro:radarr|frankbook-pro:sonarr|frankbook-pro:lidarr|\
|
||||
frankbook-pro:readarr)
|
||||
@@ -192,7 +192,7 @@ add_pending_services() {
|
||||
continue
|
||||
fi
|
||||
[[ -n "$recorded" && "$recorded" != "$REVISION" ]] || continue
|
||||
if [[ "$TARGET" == dankserver && "$service" == frank-large ]]; then continue; fi
|
||||
if [[ "$TARGET" == dankserver && "$service" == frank-dragoon ]]; then continue; fi
|
||||
if ! changed="$(python3 scripts/deploy-plan.py --target "$TARGET" \
|
||||
--repo "$REMOTE_DIR" --base "$recorded" --head "$REVISION")"; then
|
||||
echo "WARN: unable to compare state for $service; retaining it as pending" >&2
|
||||
@@ -1092,21 +1092,21 @@ deploy_anubis() {
|
||||
wait_container_healthy anubis 60 || return 1
|
||||
}
|
||||
|
||||
# frank-large is the halogen-flash-server CONTAINER (0.16.2, digest-pinned
|
||||
# through scripts/frank-large.env) serving the Quat3rnion ABLITERATED
|
||||
# frank-dragoon is the halogen-flash-server CONTAINER (0.16.2, digest-pinned
|
||||
# through scripts/frank-dragoon.env) serving the Quat3rnion ABLITERATED
|
||||
# Swift1.5 finetune of peonist's Qwen3.8-Flash-Next v2 checkpoint —
|
||||
# qwen38-flash-next-v2-swift15-abliterated.hgn (66,687,678,464 B, ~62 GiB
|
||||
# resident) + the REQUIRED n-gram lookup table + the vision tower —
|
||||
# MTP spec decode (HALOGEN_SPEC_ADAPT=0), 2 slots x 200192, image input —
|
||||
# on the Strix Halo iGPU. It stays a ROOT unit because the serve script
|
||||
# drives `podman run` directly (the frank-primary pattern): relink_unit
|
||||
# points /etc/systemd/system/frank-large.service at the repo file, boot
|
||||
# drives `podman run` directly (the frank-archon pattern): relink_unit
|
||||
# points /etc/systemd/system/frank-dragoon.service at the repo file, boot
|
||||
# persistence is that unit's [Install], and LimitMEMLOCK=infinity is
|
||||
# fleet parity. 2026-10-06 cutover from the halogen 27B-dense shape —
|
||||
# rollback = revert the swap commit's trio; the 27B payload stays on
|
||||
# disk (~/models/halogen-qwen3.8-27b).
|
||||
#
|
||||
# The gates mirror serve-frank-large.sh's predicates EXACTLY (the
|
||||
# The gates mirror serve-frank-dragoon.sh's predicates EXACTLY (the
|
||||
# 2026-10-01 crash-loop lesson): image digest in dank's podman storage,
|
||||
# each .hgn payload (checkpoint, n-gram table, vision tower) at the exact
|
||||
# byte count, the tokenizer directory holding every named file as a
|
||||
@@ -1114,23 +1114,23 @@ deploy_anubis() {
|
||||
# artifact would leave a restart-looping unit and a dark endpoint. The
|
||||
# port gate is the same as every cutover since 2026-09-16: nothing
|
||||
# starts until 7770 is released.
|
||||
LLM_LARGE_IMAGE="${LLM_LARGE_IMAGE:-ghcr.io/peonist-ai/halogen-flash-server@sha256:0c61bf84ac22308a53f5d1ca6b86806702d7039e5ebc51cae4c66621b92fe04a}"
|
||||
LLM_LARGE_CKPT="${LLM_LARGE_CKPT:-/home/dank/models/halogen-flashnext-v2/qwen38-flash-next-v2-swift15-abliterated.hgn}"
|
||||
LLM_LARGE_CKPT_BYTES="${LLM_LARGE_CKPT_BYTES:-66687678464}"
|
||||
LLM_LARGE_NGRAM="${LLM_LARGE_NGRAM:-/home/dank/models/halogen-flashnext-v2/qwen38-flash-next-ngram.hgn}"
|
||||
LLM_LARGE_NGRAM_BYTES="${LLM_LARGE_NGRAM_BYTES:-51200246144}"
|
||||
LLM_LARGE_VISION="${LLM_LARGE_VISION:-/home/dank/models/halogen-flashnext-v2/qwen38-flash-next-vision.hgn}"
|
||||
LLM_LARGE_VISION_BYTES="${LLM_LARGE_VISION_BYTES:-897916416}"
|
||||
LLM_LARGE_TOK_DIR="${LLM_LARGE_TOK_DIR:-/home/dank/models/halogen-flashnext-v2/tokenizer}"
|
||||
LLM_LARGE_TOK_FILES="${LLM_LARGE_TOK_FILES:-tokenizer.json chat_template.jinja tokenizer_config.json merges.txt vocab.json generation_config.json}"
|
||||
LLM_DRAGOON_IMAGE="${LLM_DRAGOON_IMAGE:-ghcr.io/peonist-ai/halogen-flash-server@sha256:0c61bf84ac22308a53f5d1ca6b86806702d7039e5ebc51cae4c66621b92fe04a}"
|
||||
LLM_DRAGOON_CKPT="${LLM_DRAGOON_CKPT:-/home/dank/models/halogen-flashnext-v2/qwen38-flash-next-v2-swift15-abliterated.hgn}"
|
||||
LLM_DRAGOON_CKPT_BYTES="${LLM_DRAGOON_CKPT_BYTES:-66687678464}"
|
||||
LLM_DRAGOON_NGRAM="${LLM_DRAGOON_NGRAM:-/home/dank/models/halogen-flashnext-v2/qwen38-flash-next-ngram.hgn}"
|
||||
LLM_DRAGOON_NGRAM_BYTES="${LLM_DRAGOON_NGRAM_BYTES:-51200246144}"
|
||||
LLM_DRAGOON_VISION="${LLM_DRAGOON_VISION:-/home/dank/models/halogen-flashnext-v2/qwen38-flash-next-vision.hgn}"
|
||||
LLM_DRAGOON_VISION_BYTES="${LLM_DRAGOON_VISION_BYTES:-897916416}"
|
||||
LLM_DRAGOON_TOK_DIR="${LLM_DRAGOON_TOK_DIR:-/home/dank/models/halogen-flashnext-v2/tokenizer}"
|
||||
LLM_DRAGOON_TOK_FILES="${LLM_DRAGOON_TOK_FILES:-tokenizer.json chat_template.jinja tokenizer_config.json merges.txt vocab.json generation_config.json}"
|
||||
|
||||
retire_halogen_large_quadlet() {
|
||||
retire_halogen_dragoon_quadlet() {
|
||||
local trash="$HOME/.AGENTTRASH/20260919-orca-cutover/quadlet"
|
||||
systemctl --user stop frank-large.service 2>/dev/null || true
|
||||
if [[ -e "$quadlet_unit_dir/frank-large.container" ]]; then
|
||||
systemctl --user stop frank-dragoon.service 2>/dev/null || true
|
||||
if [[ -e "$quadlet_unit_dir/frank-dragoon.container" ]]; then
|
||||
mkdir -p "$trash"
|
||||
mv -- "$quadlet_unit_dir/frank-large.container" "$trash/frank-large.container"
|
||||
echo "retired quadlet frank-large.container -> $trash"
|
||||
mv -- "$quadlet_unit_dir/frank-dragoon.container" "$trash/frank-dragoon.container"
|
||||
echo "retired quadlet frank-dragoon.container -> $trash"
|
||||
fi
|
||||
systemctl --user daemon-reload
|
||||
}
|
||||
@@ -1154,165 +1154,165 @@ wait_port_free() {
|
||||
return 1
|
||||
}
|
||||
|
||||
deploy_llm_large() {
|
||||
deploy_llm_dragoon() {
|
||||
# Refuse rather than restart-loop; every gate below has a twin in
|
||||
# serve-frank-large.sh and they must agree (2026-10-01 lesson).
|
||||
# serve-frank-dragoon.sh and they must agree (2026-10-01 lesson).
|
||||
# Capture podman output before grepping: `podman images | grep -q`
|
||||
# races under pipefail (SIGPIPE 141 becomes "no match", 2026-09-30).
|
||||
if ! grep -qF "${LLM_LARGE_IMAGE#*@}" <<<"$(podman images --format '{{.RepoDigests}}' 2>/dev/null)"; then
|
||||
echo "ERROR: halogen image absent: $LLM_LARGE_IMAGE" >&2
|
||||
echo "frank-large: pull it: podman pull ${LLM_LARGE_IMAGE%@*}" >&2
|
||||
if ! grep -qF "${LLM_DRAGOON_IMAGE#*@}" <<<"$(podman images --format '{{.RepoDigests}}' 2>/dev/null)"; then
|
||||
echo "ERROR: halogen image absent: $LLM_DRAGOON_IMAGE" >&2
|
||||
echo "frank-dragoon: pull it: podman pull ${LLM_DRAGOON_IMAGE%@*}" >&2
|
||||
return 1
|
||||
fi
|
||||
if [[ ! -f "$LLM_LARGE_CKPT" ]]; then
|
||||
echo "ERROR: halogen checkpoint absent at $LLM_LARGE_CKPT" >&2
|
||||
echo "frank-large: fetch it: bash scripts/download-frank-large-flashnext.sh" >&2
|
||||
if [[ ! -f "$LLM_DRAGOON_CKPT" ]]; then
|
||||
echo "ERROR: halogen checkpoint absent at $LLM_DRAGOON_CKPT" >&2
|
||||
echo "frank-dragoon: fetch it: bash scripts/download-frank-dragoon-flashnext.sh" >&2
|
||||
return 1
|
||||
fi
|
||||
if [[ "$(stat -c %s "$LLM_LARGE_CKPT")" != "$LLM_LARGE_CKPT_BYTES" ]]; then
|
||||
echo "ERROR: halogen checkpoint is not $LLM_LARGE_CKPT_BYTES bytes (partial download?)" >&2
|
||||
echo "frank-large: re-check: bash scripts/download-frank-large-flashnext.sh --verify-only" >&2
|
||||
if [[ "$(stat -c %s "$LLM_DRAGOON_CKPT")" != "$LLM_DRAGOON_CKPT_BYTES" ]]; then
|
||||
echo "ERROR: halogen checkpoint is not $LLM_DRAGOON_CKPT_BYTES bytes (partial download?)" >&2
|
||||
echo "frank-dragoon: re-check: bash scripts/download-frank-dragoon-flashnext.sh --verify-only" >&2
|
||||
return 1
|
||||
fi
|
||||
for gate in "$LLM_LARGE_NGRAM:$LLM_LARGE_NGRAM_BYTES:n-gram table" \
|
||||
"$LLM_LARGE_VISION:$LLM_LARGE_VISION_BYTES:vision tower"; do
|
||||
for gate in "$LLM_DRAGOON_NGRAM:$LLM_DRAGOON_NGRAM_BYTES:n-gram table" \
|
||||
"$LLM_DRAGOON_VISION:$LLM_DRAGOON_VISION_BYTES:vision tower"; do
|
||||
IFS=: read -r gpath gbytes gname <<<"$gate"
|
||||
if [[ ! -f "$gpath" ]]; then
|
||||
echo "ERROR: halogen $gname absent at $gpath" >&2
|
||||
echo "frank-large: fetch it: bash scripts/download-frank-large-flashnext.sh" >&2
|
||||
echo "frank-dragoon: fetch it: bash scripts/download-frank-dragoon-flashnext.sh" >&2
|
||||
return 1
|
||||
fi
|
||||
if [[ "$(stat -c %s "$gpath")" != "$gbytes" ]]; then
|
||||
echo "ERROR: halogen $gname is not $gbytes bytes (partial download?)" >&2
|
||||
echo "frank-large: re-check: bash scripts/download-frank-large-flashnext.sh --verify-only" >&2
|
||||
echo "frank-dragoon: re-check: bash scripts/download-frank-dragoon-flashnext.sh --verify-only" >&2
|
||||
return 1
|
||||
fi
|
||||
done
|
||||
if [[ -L "$LLM_LARGE_TOK_DIR" || ! -d "$LLM_LARGE_TOK_DIR" ]]; then
|
||||
echo "ERROR: tokenizer dir missing or a symlink at $LLM_LARGE_TOK_DIR" >&2
|
||||
echo "frank-large: fetch it: bash scripts/download-frank-large-flashnext.sh" >&2
|
||||
if [[ -L "$LLM_DRAGOON_TOK_DIR" || ! -d "$LLM_DRAGOON_TOK_DIR" ]]; then
|
||||
echo "ERROR: tokenizer dir missing or a symlink at $LLM_DRAGOON_TOK_DIR" >&2
|
||||
echo "frank-dragoon: fetch it: bash scripts/download-frank-dragoon-flashnext.sh" >&2
|
||||
return 1
|
||||
fi
|
||||
for tf in $LLM_LARGE_TOK_FILES; do
|
||||
if [[ ! -f "$LLM_LARGE_TOK_DIR/$tf" || -L "$LLM_LARGE_TOK_DIR/$tf" ]]; then
|
||||
echo "ERROR: tokenizer file missing or a symlink: $LLM_LARGE_TOK_DIR/$tf" >&2
|
||||
echo "frank-large: fetch it: bash scripts/download-frank-large-flashnext.sh" >&2
|
||||
for tf in $LLM_DRAGOON_TOK_FILES; do
|
||||
if [[ ! -f "$LLM_DRAGOON_TOK_DIR/$tf" || -L "$LLM_DRAGOON_TOK_DIR/$tf" ]]; then
|
||||
echo "ERROR: tokenizer file missing or a symlink: $LLM_DRAGOON_TOK_DIR/$tf" >&2
|
||||
echo "frank-dragoon: fetch it: bash scripts/download-frank-dragoon-flashnext.sh" >&2
|
||||
return 1
|
||||
fi
|
||||
done
|
||||
|
||||
retire_halogen_large_quadlet
|
||||
retire_halogen_dragoon_quadlet
|
||||
# The predecessor on a re-deploy is THIS unit: stop it (ExecStop stops
|
||||
# the container) before waiting on the port. The stray sweep is keyed
|
||||
# on the FULL container name, which appears in the argv of a manual
|
||||
# `podman run --name frank-large-halogen` / `podman wait` but NOT in
|
||||
# `podman run --name frank-dragoon-halogen` / `podman wait` but NOT in
|
||||
# this deployer's own command line (`bash deploy-remote.sh
|
||||
# frank-large`) — so it cannot shoot itself in the foot (the fleet
|
||||
# pkill law), and it can never match frank-secondary's llama-server.
|
||||
run_privileged systemctl stop frank-large.service 2>/dev/null || true
|
||||
pkill -f 'frank-large-halogen' 2>/dev/null || true
|
||||
podman rm -f frank-large frank-large-halogen >/dev/null 2>&1 || true
|
||||
# frank-dragoon`) — so it cannot shoot itself in the foot (the fleet
|
||||
# pkill law), and it can never match frank-zealot's llama-server.
|
||||
run_privileged systemctl stop frank-dragoon.service 2>/dev/null || true
|
||||
pkill -f 'frank-dragoon-halogen' 2>/dev/null || true
|
||||
podman rm -f frank-dragoon frank-dragoon-halogen >/dev/null 2>&1 || true
|
||||
# Nothing may start until the predecessor has released the port
|
||||
# (2026-09-16: "Deactivated successfully" was not "port free").
|
||||
wait_port_free 7770 || return 1
|
||||
relink_unit frank-large
|
||||
relink_unit frank-dragoon
|
||||
run_privileged systemctl daemon-reload
|
||||
run_privileged systemctl enable frank-large.service
|
||||
run_privileged systemctl restart frank-large.service
|
||||
wait_for_health frank-large http://127.0.0.1:7770/health 1200
|
||||
run_privileged systemctl enable frank-dragoon.service
|
||||
run_privileged systemctl restart frank-dragoon.service
|
||||
wait_for_health frank-dragoon http://127.0.0.1:7770/health 1200
|
||||
}
|
||||
|
||||
# deploy_llm_secondary — frank-secondary is llama.cpp (master build, CUDA sm_86) on
|
||||
# deploy_llm_zealot — frank-zealot is llama.cpp (master build, CUDA sm_86) on
|
||||
# the RTX 3090 as a ROOT unit: the runtime is a native binary tree under
|
||||
# ~/GitPackages/llama-master/build-cuda, so there is no container image and
|
||||
# no generated unit to avoid. relink_unit points
|
||||
# /etc/systemd/system/frank-secondary.service at the repo file and boot
|
||||
# /etc/systemd/system/frank-zealot.service at the repo file and boot
|
||||
# persistence is that unit's [Install] section.
|
||||
#
|
||||
# It is a SEPARATE endpoint on port 7771; frank-large keeps 7770. The 3090 is
|
||||
# not shared: frank-large's engine runs on the gfx1151 iGPU.
|
||||
LLM_SECONDARY_MODEL_FILE="${LLM_SECONDARY_MODEL_FILE:-/home/dank/models/Qwen35-9B-HauhauCS-Q6K/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-Q6_K.gguf}"
|
||||
LLM_SECONDARY_RUNTIME="${LLM_SECONDARY_RUNTIME:-/home/dank/GitPackages/llama-master/build-cuda/bin/llama-server}"
|
||||
# It is a SEPARATE endpoint on port 7771; frank-dragoon keeps 7770. The 3090 is
|
||||
# not shared: frank-dragoon's engine runs on the gfx1151 iGPU.
|
||||
LLM_ZEALOT_MODEL_FILE="${LLM_ZEALOT_MODEL_FILE:-/home/dank/models/Qwen35-9B-HauhauCS-Q6K/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-Q6_K.gguf}"
|
||||
LLM_ZEALOT_RUNTIME="${LLM_ZEALOT_RUNTIME:-/home/dank/GitPackages/llama-master/build-cuda/bin/llama-server}"
|
||||
# The projector IS the vision capability here: the model is natively
|
||||
# multimodal and the Q6_K file carries no vision tensors — the publisher ships
|
||||
# its own BF16 projector in the same repo, so a deploy that starts without
|
||||
# this file silently ships a text-only endpoint. Checked unconditionally, like
|
||||
# frank-large's.
|
||||
LLM_SECONDARY_MMPROJ="${LLM_SECONDARY_MMPROJ:-/home/dank/models/Qwen35-9B-HauhauCS-Q6K/mmproj-Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-BF16.gguf}"
|
||||
# frank-dragoon's.
|
||||
LLM_ZEALOT_MMPROJ="${LLM_ZEALOT_MMPROJ:-/home/dank/models/Qwen35-9B-HauhauCS-Q6K/mmproj-Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-BF16.gguf}"
|
||||
|
||||
deploy_llm_secondary() {
|
||||
deploy_llm_zealot() {
|
||||
# Refuse rather than restart-loop: a unit whose runtime or payload is
|
||||
# missing never becomes healthy, and a green deploy would leave the
|
||||
# endpoint dark with nothing in the log to say why.
|
||||
if [[ ! -x "$LLM_SECONDARY_RUNTIME" ]]; then
|
||||
echo "ERROR: llama.cpp runtime absent at $LLM_SECONDARY_RUNTIME" >&2
|
||||
echo "frank-secondary: build it (cmake -B build-cuda -DGGML_CUDA=ON" >&2
|
||||
echo "frank-secondary: -DCMAKE_CUDA_ARCHITECTURES=86 -DCMAKE_CUDA_HOST_COMPILER=/usr/bin/gcc-13" >&2
|
||||
echo "frank-secondary: && cmake --build build-cuda --target llama-server) first." >&2
|
||||
if [[ ! -x "$LLM_ZEALOT_RUNTIME" ]]; then
|
||||
echo "ERROR: llama.cpp runtime absent at $LLM_ZEALOT_RUNTIME" >&2
|
||||
echo "frank-zealot: build it (cmake -B build-cuda -DGGML_CUDA=ON" >&2
|
||||
echo "frank-zealot: -DCMAKE_CUDA_ARCHITECTURES=86 -DCMAKE_CUDA_HOST_COMPILER=/usr/bin/gcc-13" >&2
|
||||
echo "frank-zealot: && cmake --build build-cuda --target llama-server) first." >&2
|
||||
return 1
|
||||
fi
|
||||
for f in "$LLM_SECONDARY_MODEL_FILE" "$LLM_SECONDARY_MMPROJ"; do
|
||||
for f in "$LLM_ZEALOT_MODEL_FILE" "$LLM_ZEALOT_MMPROJ"; do
|
||||
if [[ ! -f "$f" ]]; then
|
||||
echo "ERROR: frank-secondary payload file absent at $f" >&2
|
||||
echo "frank-secondary: run scripts/download-frank-secondary.sh first;" >&2
|
||||
echo "frank-secondary: refusing to start a unit that cannot load." >&2
|
||||
echo "ERROR: frank-zealot payload file absent at $f" >&2
|
||||
echo "frank-zealot: run scripts/download-frank-zealot.sh first;" >&2
|
||||
echo "frank-zealot: refusing to start a unit that cannot load." >&2
|
||||
return 1
|
||||
fi
|
||||
done
|
||||
relink_unit frank-secondary
|
||||
relink_unit frank-zealot
|
||||
run_privileged systemctl daemon-reload
|
||||
run_privileged systemctl enable frank-secondary.service
|
||||
run_privileged systemctl restart frank-secondary.service
|
||||
wait_for_health frank-secondary http://127.0.0.1:7771/health 900 || return 1
|
||||
# False-green hardening (frank-large's lesson): the port answering
|
||||
run_privileged systemctl enable frank-zealot.service
|
||||
run_privileged systemctl restart frank-zealot.service
|
||||
wait_for_health frank-zealot http://127.0.0.1:7771/health 900 || return 1
|
||||
# False-green hardening (frank-dragoon's lesson): the port answering
|
||||
# proves nothing about WHO answers — the unit must be active with a
|
||||
# live MainPID, or a stray SGLang holdover is masquerading as deployed.
|
||||
local main_pid
|
||||
main_pid="$(run_privileged systemctl show -p MainPID --value frank-secondary.service)"
|
||||
main_pid="$(run_privileged systemctl show -p MainPID --value frank-zealot.service)"
|
||||
if [[ -z "$main_pid" || "$main_pid" == "0" ]]; then
|
||||
echo "FAIL: :7771 answered but frank-secondary.service has no MainPID — a stray process holds the port" >&2
|
||||
echo "FAIL: :7771 answered but frank-zealot.service has no MainPID — a stray process holds the port" >&2
|
||||
return 1
|
||||
fi
|
||||
echo "frank-secondary: health answered by unit MainPID $main_pid"
|
||||
echo "frank-zealot: health answered by unit MainPID $main_pid"
|
||||
}
|
||||
|
||||
# deploy_llm_primary — frank-primary is the radiance engine (StillDeadcode,
|
||||
# deploy_llm_archon — frank-archon is the radiance engine (StillDeadcode,
|
||||
# digest-pinned stilldeadcode/radiance image) serving the OFFICIAL
|
||||
# Qwen/Qwen3.8-Flash-Next-FP8 at native block-FP8 precision from the
|
||||
# rad-convert container qwen4exp-fp8-native.rad, on BOTH R9700s (TP=2) as a
|
||||
# ROOT unit whose serve script drives `podman run` directly (the engine is
|
||||
# the image entrypoint; the image lives in dank's rootless podman storage).
|
||||
# 2026-10-05 cutover from FreeToken (pre-cutover tag
|
||||
# frank-primary-freetoken-pr587-20261005); before that, the tcclaviger vLLM
|
||||
# fork (tag frank-primary-vllm-shapeG-20261003). Same port and alias; the
|
||||
# frank-archon-freetoken-pr587-20261005); before that, the tcclaviger vLLM
|
||||
# fork (tag frank-archon-vllm-shapeG-20261003). Same port and alias; the
|
||||
# harness models.yml id is unchanged.
|
||||
#
|
||||
# Gates: the image must exist under its digest ref in dank's rootless
|
||||
# storage (FRANK_PRIMARY_IMAGE), the .rad container file must exist at the
|
||||
# env's size floor (FRANK_PRIMARY_MODEL_FILE >= FRANK_PRIMARY_RAD_MIN_MIB —
|
||||
# storage (FRANK_ARCHON_IMAGE), the .rad container file must exist at the
|
||||
# env's size floor (FRANK_ARCHON_MODEL_FILE >= FRANK_ARCHON_RAD_MIN_MIB —
|
||||
# a truncated convert is a guaranteed long-timeout boot), and the unit env
|
||||
# must be complete. Per-file sha256 verification is the fetch script's job
|
||||
# at download time and rad-convert/rad-info's job at build time, never
|
||||
# re-hashed here.
|
||||
LLM_PRIMARY_CONTAINER=frank-primary
|
||||
LLM_PRIMARY_LEGACY_CONTAINERS="frank-primary-qwen frank-primary-r9v qwen-fp8 glm-probe"
|
||||
LLM_ARCHON_CONTAINER=frank-archon
|
||||
LLM_ARCHON_LEGACY_CONTAINERS="frank-archon-qwen frank-archon-r9v qwen-fp8 glm-probe"
|
||||
|
||||
deploy_llm_primary() {
|
||||
deploy_llm_archon() {
|
||||
# Refuse rather than restart-loop: a unit whose image or payload is
|
||||
# missing never becomes healthy, and a green deploy would leave the
|
||||
# endpoint dark with nothing in the log to say why.
|
||||
local env_file="/home/dank/serverAppConfigs/scripts/frank-primary.env"
|
||||
local env_file="/home/dank/serverAppConfigs/scripts/frank-archon.env"
|
||||
local image model_dir model_file rad_min mib
|
||||
if [[ ! -f "$env_file" ]]; then
|
||||
echo "ERROR: frank-primary env file absent: $env_file" >&2
|
||||
echo "ERROR: frank-archon env file absent: $env_file" >&2
|
||||
return 1
|
||||
fi
|
||||
image="$(sed -n 's/^FRANK_PRIMARY_IMAGE=//p' "$env_file" | tail -1)"
|
||||
model_dir="$(sed -n 's/^FRANK_PRIMARY_MODEL_DIR=//p' "$env_file" | tail -1)"
|
||||
model_file="$(sed -n 's/^FRANK_PRIMARY_MODEL_FILE=//p' "$env_file" | tail -1)"
|
||||
rad_min="$(sed -n 's/^FRANK_PRIMARY_RAD_MIN_MIB=//p' "$env_file" | tail -1)"
|
||||
image="$(sed -n 's/^FRANK_ARCHON_IMAGE=//p' "$env_file" | tail -1)"
|
||||
model_dir="$(sed -n 's/^FRANK_ARCHON_MODEL_DIR=//p' "$env_file" | tail -1)"
|
||||
model_file="$(sed -n 's/^FRANK_ARCHON_MODEL_FILE=//p' "$env_file" | tail -1)"
|
||||
rad_min="$(sed -n 's/^FRANK_ARCHON_RAD_MIN_MIB=//p' "$env_file" | tail -1)"
|
||||
if [[ -z "$image" || -z "$model_dir" || -z "$model_file" || -z "$rad_min" ]]; then
|
||||
echo "ERROR: frank-primary.env missing FRANK_PRIMARY_IMAGE/MODEL_DIR/MODEL_FILE/RAD_MIN_MIB" >&2
|
||||
echo "ERROR: frank-archon.env missing FRANK_ARCHON_IMAGE/MODEL_DIR/MODEL_FILE/RAD_MIN_MIB" >&2
|
||||
return 1
|
||||
fi
|
||||
# The image gate is the digest ref itself: a name@sha256 ref exists in
|
||||
@@ -1320,18 +1320,18 @@ deploy_llm_primary() {
|
||||
# pipefail/grep race (the 2026-09-30 lesson).
|
||||
if ! podman image exists "$image"; then
|
||||
echo "ERROR: runtime image absent from storage: $image" >&2
|
||||
echo "frank-primary: podman pull docker://stilldeadcode/radiance:latest" >&2
|
||||
echo "frank-archon: podman pull docker://stilldeadcode/radiance:latest" >&2
|
||||
return 1
|
||||
fi
|
||||
if [[ ! -f "$model_dir/$model_file" ]]; then
|
||||
echo "ERROR: .rad container missing: $model_dir/$model_file" >&2
|
||||
echo "frank-primary: run scripts/build-frank-primary-rad.sh" >&2
|
||||
echo "frank-archon: run scripts/build-frank-archon-rad.sh" >&2
|
||||
return 1
|
||||
fi
|
||||
mib=$(( $(stat -c %s "$model_dir/$model_file") / 1048576 ))
|
||||
if [[ "$mib" -lt "$rad_min" ]]; then
|
||||
echo "ERROR: .rad container too small: $model_dir/$model_file is ${mib} MiB, want >= $rad_min" >&2
|
||||
echo "frank-primary: rebuild it (scripts/build-frank-primary-rad.sh --force)" >&2
|
||||
echo "frank-archon: rebuild it (scripts/build-frank-archon-rad.sh --force)" >&2
|
||||
return 1
|
||||
fi
|
||||
|
||||
@@ -1343,19 +1343,19 @@ deploy_llm_primary() {
|
||||
# The legacy identities (the retired R9V container, the ad hoc
|
||||
# experiment container qwen-fp8, the retired glm-probe) hold the same
|
||||
# GPUs and die here too.
|
||||
run_privileged systemctl stop frank-primary.service 2>/dev/null || true
|
||||
run_privileged systemctl stop frank-archon.service 2>/dev/null || true
|
||||
local ctr
|
||||
for ctr in $LLM_PRIMARY_LEGACY_CONTAINERS "$LLM_PRIMARY_CONTAINER"; do
|
||||
for ctr in $LLM_ARCHON_LEGACY_CONTAINERS "$LLM_ARCHON_CONTAINER"; do
|
||||
podman rm -f "$ctr" >/dev/null 2>&1 || true
|
||||
done
|
||||
# Nothing starts until the port is released: the lucebox cutover
|
||||
# (2026-09-26) and the frank-large cutover (2026-09-16) both failed
|
||||
# (2026-09-26) and the frank-dragoon cutover (2026-09-16) both failed
|
||||
# exactly here when the next engine bound 7770 a second too early.
|
||||
wait_port_free 7770 || return 1
|
||||
relink_unit frank-primary
|
||||
relink_unit frank-archon
|
||||
run_privileged systemctl daemon-reload
|
||||
run_privileged systemctl enable frank-primary.service
|
||||
run_privileged systemctl restart frank-primary.service
|
||||
run_privileged systemctl enable frank-archon.service
|
||||
run_privileged systemctl restart frank-archon.service
|
||||
# Cold start: .rad load + PLE pin + expert host-pool upload (the
|
||||
# publisher's compose healthcheck allows a 15-minute start_period).
|
||||
# Parity with every predecessor on this port. The HTTP listener binds
|
||||
@@ -1366,14 +1366,14 @@ deploy_llm_primary() {
|
||||
local i ok=0
|
||||
for ((i=1; i<=900; i++)); do
|
||||
if curl -fsS http://127.0.0.1:7770/health 2>/dev/null >/dev/null; then
|
||||
echo "frank-primary engine healthy after approximately $((i * 2))s"
|
||||
echo "frank-archon engine healthy after approximately $((i * 2))s"
|
||||
ok=1
|
||||
break
|
||||
fi
|
||||
sleep 2
|
||||
done
|
||||
if [[ "$ok" != 1 ]]; then
|
||||
echo "FAIL: frank-primary /health never answered 200 in 1800s" >&2
|
||||
echo "FAIL: frank-archon /health never answered 200 in 1800s" >&2
|
||||
return 1
|
||||
fi
|
||||
# False-green hardening (the 2026-09-26 lesson): a bare curl against the
|
||||
@@ -1381,12 +1381,12 @@ deploy_llm_primary() {
|
||||
# it while the unit is stopped. The deploy is only green if the unit
|
||||
# itself is active with a live MainPID behind the health answer.
|
||||
local main_pid
|
||||
main_pid="$(run_privileged systemctl show -p MainPID --value frank-primary.service)"
|
||||
main_pid="$(run_privileged systemctl show -p MainPID --value frank-archon.service)"
|
||||
if [[ -z "$main_pid" || "$main_pid" == "0" ]]; then
|
||||
echo "FAIL: :7770 answered but frank-primary.service has no MainPID — a stray process holds the port" >&2
|
||||
echo "FAIL: :7770 answered but frank-archon.service has no MainPID — a stray process holds the port" >&2
|
||||
return 1
|
||||
fi
|
||||
echo "frank-primary: health answered by unit MainPID $main_pid"
|
||||
echo "frank-archon: health answered by unit MainPID $main_pid"
|
||||
}
|
||||
|
||||
wait_for_health() {
|
||||
@@ -1573,9 +1573,9 @@ deploy_service() {
|
||||
anubis) deploy_anubis ;;
|
||||
seerr) deploy_seerr ;;
|
||||
marreta) deploy_marreta ;;
|
||||
frank-large) deploy_llm_large ;;
|
||||
frank-secondary) deploy_llm_secondary ;;
|
||||
frank-primary) deploy_llm_primary ;;
|
||||
frank-dragoon) deploy_llm_dragoon ;;
|
||||
frank-zealot) deploy_llm_zealot ;;
|
||||
frank-archon) deploy_llm_archon ;;
|
||||
hermes|hermes-dashboard|hermes-webui) deploy_hermes ;;
|
||||
romm|romm-mariadb|romm-redis|mariadb|redis) deploy_romm_stack "$service" ;;
|
||||
jellyfin) deploy_jellyfin ;;
|
||||
|
||||
Reference in New Issue
Block a user