Files
serverAppConfigs/tests/deployment_scoping.bats
T
Frankandomp 53ef121180 feat(frank-dragoon): run the XDNA2 NPU lane beside the flash model
halogen-flash-server already ships an NPU path on the pin we run: for each
model named in HALOGEN_NPU_MODELS it loads the vendor's precompiled AIE
programs (XDNA2 executes only AIE-compiled graphs) and answers them on
/v1/embeddings inside the SAME container behind port 7770. That gives the
fleet an in-house embedding endpoint without touching the iGPU trunk.

The lane is opt-in and one line wide: HALOGEN_NPU_MODELS blank is the
pre-lane endpoint byte for byte (no device, no mounts, no engine env).

The three host preconditions the vendor names are gated in the serve script
and mirrored in the deployer (the 2026-10-01 twin law), each refused by name:
  - the staged model files. /models is read-only and HALOGEN_DOWNLOAD stays
    unset so the container opens no outbound connection at boot, so
    scripts/download-frank-dragoon-npu.sh stages them from the pinned
    revision with the catalog's own byte counts and sha256s (the engine
    re-checks both at boot);
  - the distro XRT's libxrt_coreutil/libxrt_core/libxrt_driver_xdna, each
    mounted twice — where the image looks for XRT and at its own path —
    because those libraries find each other where they were installed and
    an /opt/xilinx/xrt of symlinks dangles inside the container;
  - the GPU fabric clock HELD. On Strix Halo the iGPU and the NPU co-running
    hang the machine (and corrupt NPU results) while FCLK changes speed, and
    halogen refuses to start in that state; it cannot read host sysfs from
    inside, so the hold is proven host-side. dankclaw/host/ carries the
    vendor's halogen-fabric-clock{,.service} verbatim at tag v0.16.2 (sha256
    a3a4f7f4e0142e71… / 5f9f1cc4c85a1c02…); the deployer installs, enables
    and gates it only while the lane is named, and releases the clock plus
    drops the boot hook when it is not.

After health, the deployer's lane gate is a real embedding through
/v1/embeddings — a 200 on /health proves nothing about the NPU programs.

Planner: dankclaw/host/halogen-fabric-clock* re-dispatches frank-dragoon
(the deployer installs it); dankclaw/host/grub and the fetch script plan
nothing.

Seam: 11 new tests — the off arm really renders nothing lane-specific, the
on arm renders the device/mounts/env, every missing precondition refuses by
name, the deployer twins and the host unit shape are pinned.

Co-Authored-By: omp <omp@dankclaw>
2026-10-19 21:22:50 -07:00

268 lines
11 KiB
Bash

#!/usr/bin/env bats
# Seam: service-scoped deployment planning.
# A repository commit can contain changes for several workloads while only a
# subset is safe to restart. The planner must keep inference isolated from
# unrelated service changes and treat docs-only changes as a no-op.
load helpers
PLANNER="$REPO_ROOT/scripts/deploy-plan.py"
REMOTE_DEPLOY="$REPO_ROOT/scripts/deploy-remote.sh"
@test "deployment planner maps SearXNG changes to SearXNG only" {
run python3 "$PLANNER" --target dankclaw --paths \
shared/searxng/settings.yml serverAppConfigs-docs/Dankclaw/SearXNG.md
[ "$status" -eq 0 ]
[ "$output" = "searxng" ]
}
@test "deployment planner maps large-model changes to the large model only" {
run python3 "$PLANNER" --target dankclaw --paths \
scripts/frank-dragoon.env
[ "$status" -eq 0 ]
[ "$output" = "frank-dragoon" ]
}
@test "the retired NPU endpoint is absent from the deployment inventory" {
! grep -q '"frank-npu"' "$PLANNER"
! grep -q 'frank_npu\|frank-npu' "$REMOTE_DEPLOY"
}
@test "the retired ik chat template plans nothing, and its archive is still here" {
# scripts/chat-template.jinja existed only for the ik_llama.cpp runtime
# (retired 2026-09-16 in favour of halogen-flash-server again). The
# llama.cpp frank-zealot runtime serves the template the GGUF itself
# carries, which is the one with reasoning_effort, preserve_thinking and
# the tool-call grammar. Editing the archive must deploy nothing -- and the
# archive must still be present, so this cannot pass by the file having
# vanished.
[ -f "$REPO_ROOT/scripts/.AGENTTRASH/chat-template.jinja.ik-llama-qwen-sharp" ]
run python3 "$PLANNER" --target dankclaw --paths scripts/chat-template.jinja
[ "$status" -eq 0 ]
[ -z "$output" ]
run python3 "$PLANNER" --target dankserver --paths scripts/chat-template.jinja
[ "$status" -eq 0 ]
[ -z "$output" ]
}
@test "the retired frank-medium tree plans nothing, from any archive" {
# frank-medium left the live tree on 2026-09-26 — first the radiance
# Quadlet (and its vLLM replica archive before it), then the llama.cpp
# layersplit trio and its fetch tooling. Every shape is archive material
# now, and a planner rule matching any of them would restart a service
# nobody maintains.
run python3 "$PLANNER" --target dankserver --paths \
dankserver/.AGENTTRASH/20260916-vllm-radiance/frank-medium-a.container \
dankserver/.AGENTTRASH/20260926-frank-medium-radiance/frank-medium.container \
dankserver/.AGENTTRASH/20260926-frank-medium-radiance/radiance-entrypoint.sh \
scripts/.AGENTTRASH/20260920-llama-layersplit/frank-medium.env.llamacpp-layersplit \
scripts/.AGENTTRASH/20260926-frank-medium-radiance/download-frank-medium-gguf.sh \
scripts/.AGENTTRASH/20260926-frank-medium-radiance/swap-frank-medium.sh
[ "$status" -eq 0 ]
[ -z "$output" ]
}
@test "deployment planner maps the frank-archon trio to frank-archon only" {
# The root-unit shape since the 2026-09-26 swap: unit, env and serve
# script live in scripts/ and select exactly frank-archon. The
# download script fetches host-side state and must select nothing, and
# the lucebox quadlet-era tree in dated trash plans nothing either.
run python3 "$PLANNER" --target dankserver --paths \
scripts/frank-archon.env \
scripts/frank-archon.service \
scripts/serve-frank-archon.sh
[ "$status" -eq 0 ]
[ "$output" = "frank-archon" ]
run python3 "$PLANNER" --target dankserver --paths \
scripts/download-frank-archon.sh \
dankserver/.AGENTTRASH/20260926-llamacpp-cutover/frank-archon.container
[ "$status" -eq 0 ]
[ -z "$output" ]
}
@test "the small endpoint is Dankclaw's again, and Dankserver's copy stays retired" {
run python3 "$PLANNER" --target dankclaw --paths \
scripts/frank-zealot.env scripts/frank-zealot.service scripts/serve-frank-zealot.sh
[ "$status" -eq 0 ]
[ "$output" = "frank-zealot" ]
# frank-zealot runs on Dankclaw on the RTX 3090; the Dankserver endpoint of
# that name was retired with the FreeToken runtime on 2026-09-15 and must
# not come back through a planner mapping.
run python3 "$PLANNER" --target dankserver --paths \
scripts/frank-zealot.env scripts/frank-zealot.service scripts/serve-frank-zealot.sh
[ "$status" -eq 0 ]
[ -z "$output" ]
}
@test "documentation-only changes plan no runtime deployment" {
run python3 "$PLANNER" --target dankclaw --paths \
serverAppConfigs-docs/Architecture/Deployment\ Flow.md serverAppConfigs-docs/Dankclaw/SearXNG.md
[ "$status" -eq 0 ]
[ -z "$output" ]
}
@test "deployment planner maps shared config to one service" {
run python3 "$PLANNER" --target dankclaw --paths \
shared/prometheus/prometheus.yml
[ "$status" -eq 0 ]
[ "$output" = "prometheus" ]
}
@test "deployment planner maps shared observability configs independently" {
run python3 "$PLANNER" --target dankclaw --paths shared/loki/loki-config.yaml
[ "$status" -eq 0 ]
[ "$output" = "loki" ]
run python3 "$PLANNER" --target dankclaw --paths shared/alloy/config.alloy
[ "$status" -eq 0 ]
[ "$output" = "alloy" ]
}
@test "deployment planner maps service-owned non-compose files" {
run python3 "$PLANNER" --target dankclaw --paths dankclaw/hermes/config.yaml.example
[ "$status" -eq 0 ]
[ "$output" = "hermes" ]
}
@test "homepage is owned by Dankclaw's consolidated proxy" {
run python3 "$PLANNER" --target dankserver --paths shared/homepage/index.html
[ "$status" -eq 0 ]
[ -z "$output" ]
}
@test "compose planner narrows a compose edit to the changed service" {
local base head
base=$(git -C "$REPO_ROOT" rev-parse HEAD)
head=$(git -C "$REPO_ROOT" rev-parse HEAD)
run python3 "$PLANNER" --target dankclaw --repo "$REPO_ROOT" \
--base "$base" --head "$head" --paths dankclaw/compose.yaml
[ "$status" -eq 0 ]
[ -z "$output" ]
}
@test "network-coupled SearXNG config changes include the required peers" {
run python3 "$PLANNER" --target dankclaw --paths \
dankclaw/searxng/quadlet/gluetun.container
[ "$status" -eq 0 ]
[ "$output" = $'gluetun\nsearxng\nmarreta' ]
}
@test "retiring the standalone Gitea proxy deploys the canonical Caddy" {
run python3 "$PLANNER" --target dankclaw --paths \
dankclaw/gitea/quadlet/gitea-caddy.container
[ "$status" -eq 0 ]
[ "$output" = "caddy" ]
}
@test "Gitea network changes exclude the retired standalone proxy" {
run python3 "$PLANNER" --target dankclaw --paths \
dankclaw/gitea/quadlet/gitea.network
[ "$status" -eq 0 ]
[ "$output" = $'gitea-postgres\ngitea-server' ]
}
@test "frankbook-pro gluetun changes carry the whole netns family; arr changes stay scoped" {
run python3 "$PLANNER" --target frankbook-pro --paths \
frankbook-pro/gluetun/quadlet/gluetun.container
[ "$status" -eq 0 ]
[ "$output" = $'gluetun\nprowlarr\nqbittorrent\nradarr\nsonarr\nlidarr\nreadarr' ]
run python3 "$PLANNER" --target frankbook-pro --paths \
frankbook-pro/sonarr/quadlet/sonarr.container
[ "$status" -eq 0 ]
[ "$output" = "sonarr" ]
}
@test "remote Caddy deployment no longer blocks on the retired Gitea proxy" {
! grep -q 'refusing to replace it with caddy' "$REMOTE_DEPLOY"
! grep -q 'podman container exists gitea-caddy &&' "$REMOTE_DEPLOY"
}
@test "remote Caddy deployment retires the installed Gitea proxy" {
grep -q 'retire_legacy_gitea_caddy' "$REMOTE_DEPLOY"
grep -q 'systemctl --user stop gitea-caddy.service' "$REMOTE_DEPLOY"
grep -q 'systemctl --user disable gitea-caddy.service' "$REMOTE_DEPLOY"
grep -q 'gitea-caddy.container' "$REMOTE_DEPLOY"
grep -q 'HOME/.AGENTTRASH' "$REMOTE_DEPLOY"
grep -q 'stage_legacy_gitea_caddy_state' "$REMOTE_DEPLOY"
}
@test "remote deployment inventory no longer accepts gitea-caddy as a service" {
! grep -qE 'dankclaw:gitea-caddy|gitea-caddy\) deploy' "$REPO_ROOT/scripts/deploy.sh" "$REPO_ROOT/scripts/deploy-remote.sh"
! grep -q '"gitea-caddy"' "$REPO_ROOT/scripts/deploy-plan.py"
}
@test "remote deployer carries per-service deployment state" {
[ -x "$REMOTE_DEPLOY" ]
grep -q 'deploy-state' "$REMOTE_DEPLOY"
grep -q 'STATE\[' "$REMOTE_DEPLOY"
grep -q 'mark_status.*pending\|status=pending' "$REMOTE_DEPLOY"
grep -q 'mark_status.*deployed\|status=deployed' "$REMOTE_DEPLOY"
}
@test "remote deployer routes inference restarts through selected handlers" {
# The runner may restart inference only from the service-dispatch path. It
# must not contain a host-wide restart loop.
grep -q 'deploy_llm_dragoon' "$REMOTE_DEPLOY"
grep -q 'deploy_llm_archon' "$REMOTE_DEPLOY"
grep -q 'deploy_service' "$REMOTE_DEPLOY"
! grep -qE 'for .*frank-(small|large|npu)-?' "$REMOTE_DEPLOY"
}
@test "remote runner rejects services belonging to the other host" {
run env DEPLOY_STATE_DIR="$(mktemp -d)" REMOTE_DIR="$REPO_ROOT" \
bash "$REMOTE_DEPLOY" dankserver "$(git rev-parse HEAD)" frank-default-large
[ "$status" -eq 2 ]
}
@test "remote runner recognizes a pending service at the same revision" {
# Contract superseded 2026-09-17: recognition used to mean "retry and
# hard-fail at the dispatcher" (exit 2), which let a retired service's
# stale pending entry (frank-default-sightsound) block every deploy
# before the e2e gate. Recognition now means: name the entry, prune it
# to the trash, and keep the run going.
local state_dir="$(mktemp -d)"
printf 'revision=%s\nstatus=pending\n' "$(git rev-parse HEAD)" > "$state_dir/unknown-service"
run env DEPLOY_STATE_DIR="$state_dir" REMOTE_DIR="$REPO_ROOT" HOME="$(mktemp -d)" \
bash "$REMOTE_DEPLOY" dankclaw "$(git rev-parse HEAD)" --pending
[ "$status" -eq 0 ]
[[ "$output" == *"unknown-service"* ]]
[ ! -e "$state_dir/unknown-service" ]
}
@test "top-level deployer delegates to the service-scoped remote runner" {
grep -q 'deploy-remote.sh' "$REPO_ROOT/scripts/deploy.sh"
grep -qE 'SERVICE|service' "$REPO_ROOT/scripts/deploy.sh"
grep -q 'OLD_REVISION' "$REPO_ROOT/scripts/deploy.sh"
grep -q 'OLD_REVISION\|old checkout revision' "$REPO_ROOT/scripts/deploy.sh"
}
@test "legacy service deploy wrappers delegate to the scoped deployer" {
for script in deploy-searxng-quadlet.sh deploy-pihole-quadlet.sh deploy-open-webui-quadlet.sh; do
grep -q 'deploy.sh' "$REPO_ROOT/scripts/$script" || {
echo "$script does not delegate to deploy.sh"
return 1
}
done
}
@test "the fabric-clock host unit re-dispatches frank-dragoon and stages nothing else" {
# The hold is the NPU lane's boot precondition and the deployer installs and
# gates it, so a change to it has to reach the endpoint. The tracked boot
# line under the same directory is a hand-taken reboot decision and must
# never plan a restart, and staging the NPU model files is host-side state
# like every other download script.
run python3 "$PLANNER" --target dankclaw --paths \
dankclaw/host/halogen-fabric-clock dankclaw/host/halogen-fabric-clock.service
[ "$status" -eq 0 ]
[ "$output" = "frank-dragoon" ]
run python3 "$PLANNER" --target dankclaw --paths dankclaw/host/grub
[ "$status" -eq 0 ]
[ -z "$output" ]
run python3 "$PLANNER" --target dankclaw --paths scripts/download-frank-dragoon-npu.sh
[ "$status" -eq 0 ]
[ -z "$output" ]
}