Frank
76aaa2543b
The harness clamps max_tokens to min(45056, contextWindow - est - 4096), its chars/4 est under-counts the rendered prompt by ~3 % (measured: 152,938 -> 157,388 and 158,906 -> 165,301), and compaction fires only at 85 % -- so with window == engine ceiling 200192, every request in the est ~146k-184k zone was a guaranteed 400. HALOGEN_CTX=262144 (native) + KV pool 524288; harness window 217088 = ceiling - 45k absorbs the estimate error (worst-case request ~219k <= 262144). models.yml updated out-of-repo: contextWindow 217088, maxTokens 45056.
373 lines
17 KiB
Bash
Executable File
373 lines
17 KiB
Bash
Executable File
#!/usr/bin/env bats
|
||
# Seam: frank-large serves the Quat3rnion ABLITERATED Swift1.5 finetune of
|
||
# peonist's Qwen3.8-Flash-Next v2 checkpoint (a .hgn flash-server payload)
|
||
# on the Strix Halo iGPU through the halogen-flash-server CONTAINER (0.16.2,
|
||
# digest-pinned), driven by the root unit's serve script — two 262,144-token
|
||
# slots with the MTP head always on (HALOGEN_SPEC_ADAPT=0) and the vision
|
||
# tower mounted. 2026-10-06 cutover from the halogen 27B-dense shape.
|
||
#
|
||
# This seam exists because the artifacts are a triangle that must agree on
|
||
# exact strings the engine reads: the image DIGEST, the checkpoint/n-gram/
|
||
# vision file names AND byte counts inside the /models mount, and the
|
||
# tokenizer's flat-file shape (a HF cache snapshot's symlinks dangle inside
|
||
# the container). A serve gate and a deployer gate that disagree is the
|
||
# 2026-10-01 crash-loop; both sides are pinned here, plus the one engine
|
||
# law the card is emphatic about: HALOGEN_SPEC_ADAPT=0 — the default
|
||
# adaptive policy silently disables the MTP head per request and HALVES
|
||
# decode.
|
||
#
|
||
# Everything is tested from what an operator or supervisor can observe —
|
||
# the command line podman would run, the exit code, the deployer's error
|
||
# text — never from anything inside the engine.
|
||
|
||
setup() {
|
||
ROOT="$(cd "$(dirname "$BATS_TEST_FILENAME")/.." && pwd)"
|
||
SERVE="$ROOT/scripts/serve-frank-large.sh"
|
||
ENV_FILE="$ROOT/scripts/frank-large.env"
|
||
UNIT="$ROOT/scripts/frank-large.service"
|
||
DEPLOYER="$ROOT/scripts/deploy-remote.sh"
|
||
BUILD="$ROOT/scripts/build-rocmfpx.sh"
|
||
TEST_TMP="$(mktemp -d)"
|
||
touch "$TEST_TMP/empty.env"
|
||
}
|
||
|
||
teardown() {
|
||
rm -rf "$TEST_TMP"
|
||
}
|
||
|
||
# podman_stub — a fake podman on PATH that prints the argv of `run` and
|
||
# `wait` and answers `images` with whatever digests the test names, so
|
||
# "what would the supervisor run" is observable output and the digest
|
||
# gate is testable without a 3.6 GB image.
|
||
podman_stub() {
|
||
mkdir -p "$TEST_TMP/bin"
|
||
cat > "$TEST_TMP/bin/podman" <<'STUB'
|
||
#!/usr/bin/env bash
|
||
case "$1" in
|
||
images) printf '%s\n' "${STUB_DIGESTS:-}" ;;
|
||
rm) exit 0 ;;
|
||
run|wait) echo "PODMAN $*"; exit "${STUB_WAIT_RC:-0}" ;;
|
||
*) exit 0 ;;
|
||
esac
|
||
STUB
|
||
chmod +x "$TEST_TMP/bin/podman"
|
||
}
|
||
|
||
# good_env — the minimum env the serve script demands, with the digest
|
||
# stub agrees on and zero-byte artifacts passing the size gates.
|
||
good_env() {
|
||
: > "$TEST_TMP/empty.env"
|
||
touch "$TEST_TMP/qwen.hgn" "$TEST_TMP/ngram.hgn" "$TEST_TMP/vision.hgn"
|
||
mkdir -p "$TEST_TMP/tokenizer" && touch "$TEST_TMP/tokenizer/tok.json"
|
||
# A host with plenty of RAM: the pin-gate preflight passes by default so
|
||
# the artifact gates below are the thing under test.
|
||
printf 'MemTotal: 127108112 kB\nMemAvailable: 100000000 kB\n' > "$TEST_TMP/meminfo"
|
||
GOOD_ENV=(
|
||
"FRANK_LARGE_ENV_FILE=$TEST_TMP/empty.env"
|
||
"FRANK_LARGE_IMAGE=ghcr.io/peonist-ai/halogen-flash-server@sha256:cafe"
|
||
"FRANK_LARGE_CONTAINER=frank-large-halogen"
|
||
"FRANK_LARGE_LEGACY_CONTAINERS=frank-large"
|
||
"FRANK_LARGE_DEV_KFD=$TEST_TMP/qwen.hgn"
|
||
"FRANK_LARGE_DEV_DRI=$TEST_TMP"
|
||
"FRANK_LARGE_LOG=$TEST_TMP/serve.log"
|
||
"FRANK_LARGE_PUBLISH=7770:8731"
|
||
"FRANK_LARGE_MODEL_DIR=$TEST_TMP"
|
||
"FRANK_LARGE_CHECKPOINT=qwen.hgn"
|
||
"FRANK_LARGE_CHECKPOINT_BYTES=0"
|
||
"FRANK_LARGE_NGRAM_TABLE=ngram.hgn"
|
||
"FRANK_LARGE_NGRAM_BYTES=0"
|
||
"FRANK_LARGE_VISION_TOWER=vision.hgn"
|
||
"FRANK_LARGE_VISION_BYTES=0"
|
||
"FRANK_LARGE_TOKENIZER_FILES=tok.json"
|
||
"HALOGEN_MODEL_ID=frank-large"
|
||
"HALOGEN_CTX=262144"
|
||
"HALOGEN_KV_POOL_POSITIONS=524288"
|
||
"HALOGEN_KV_SLOTS=2"
|
||
"HALOGEN_SPEC_ADAPT=0"
|
||
"HALOGEN_MAX_TOK=8192"
|
||
"FRANK_LARGE_MEMINFO=$TEST_TMP/meminfo"
|
||
"STUB_DIGESTS=localhost/x ghcr.io/peonist-ai/halogen-flash-server@sha256:cafe"
|
||
)
|
||
}
|
||
|
||
@test "the env file defines the flash-server deployment values" {
|
||
grep -qE '^FRANK_LARGE_IMAGE=ghcr\.io/peonist-ai/halogen-flash-server@sha256:[0-9a-f]{64}$' "$ENV_FILE"
|
||
grep -qE '^FRANK_LARGE_CONTAINER=frank-large-halogen$' "$ENV_FILE"
|
||
grep -qE '^FRANK_LARGE_PUBLISH=7770:8731$' "$ENV_FILE"
|
||
grep -qE '^FRANK_LARGE_CHECKPOINT=.*\.hgn$' "$ENV_FILE"
|
||
grep -qE '^FRANK_LARGE_CHECKPOINT_BYTES=[0-9]+$' "$ENV_FILE"
|
||
grep -qE '^FRANK_LARGE_CHECKPOINT_SHA256=[0-9a-f]{64}$' "$ENV_FILE"
|
||
grep -qE '^FRANK_LARGE_NGRAM_TABLE=.*\.hgn$' "$ENV_FILE"
|
||
grep -qE '^FRANK_LARGE_NGRAM_BYTES=[0-9]+$' "$ENV_FILE"
|
||
grep -qE '^FRANK_LARGE_NGRAM_SHA256=[0-9a-f]{64}$' "$ENV_FILE"
|
||
grep -qE '^FRANK_LARGE_VISION_TOWER=.*\.hgn$' "$ENV_FILE"
|
||
grep -qE '^FRANK_LARGE_VISION_BYTES=[0-9]+$' "$ENV_FILE"
|
||
grep -qE '^FRANK_LARGE_VISION_SHA256=[0-9a-f]{64}$' "$ENV_FILE"
|
||
grep -qE '^FRANK_LARGE_TOKENIZER_FILES="tokenizer\.json( [a-z_.]+)+"$' "$ENV_FILE"
|
||
grep -qE '^HALOGEN_MODEL_ID=frank-large$' "$ENV_FILE"
|
||
grep -qE '^HALOGEN_CTX=[0-9]+$' "$ENV_FILE"
|
||
}
|
||
|
||
@test "the head stays on: adaptive spec must stay 0 and the window shape pinned" {
|
||
# The card is emphatic: the default adaptive policy turns the MTP head
|
||
# off for whole requests after low acceptance and HALVES decode. The
|
||
# two-slot law does NOT carry over from the 27B engine — on this line
|
||
# batching and speculation coexist (the card's quickstart ships 2
|
||
# slots WITH the head), so 2 is concurrent capacity, not a tax.
|
||
grep -qE '^HALOGEN_SPEC_ADAPT=0$' "$ENV_FILE"
|
||
grep -qE '^HALOGEN_KV_SLOTS=2$' "$ENV_FILE"
|
||
# The cap/timeout pair is coupled (FLAGS.md table): a request at the
|
||
# cap must not outlast the queue timeout, or everyone queued behind
|
||
# it eats a 503. The per-request default must stay under the cap.
|
||
grep -qE '^HALOGEN_MAX_TOK=[0-9]+$' "$ENV_FILE"
|
||
grep -qE '^HALOGEN_MAX_TOKENS_CAP=[0-9]+$' "$ENV_FILE"
|
||
grep -qE '^HALOGEN_QUEUE_TIMEOUT=[0-9]+$' "$ENV_FILE"
|
||
mt="$(sed -nE 's/^HALOGEN_MAX_TOK=([0-9]+)$/\1/p' "$ENV_FILE")"
|
||
cap="$(sed -nE 's/^HALOGEN_MAX_TOKENS_CAP=([0-9]+)$/\1/p' "$ENV_FILE")"
|
||
[ "$mt" -le "$cap" ]
|
||
}
|
||
|
||
@test "the serve script refuses when there is no GPU to serve on" {
|
||
podman_stub
|
||
good_env
|
||
run env PATH="$TEST_TMP/bin:$PATH" "${GOOD_ENV[@]}" \
|
||
FRANK_LARGE_DEV_KFD="$TEST_TMP/absent-node" "$SERVE"
|
||
[ "$status" -ne 0 ]
|
||
[[ "$output" == *"no gfx1151 to serve on"* ]]
|
||
}
|
||
|
||
@test "the pool product and memory ledger fit unified memory with margin" {
|
||
# Pool arithmetic is the engine's documented product: the explicit
|
||
# HALOGEN_KV_POOL_POSITIONS must equal slots x ctx, and KV costs
|
||
# ~28 KiB/position (FLAGS.md). Against it: ~62 GiB resident weights,
|
||
# the arena scratch 3.8 + 8.4*(MAX_TOK/16384) GiB, the vision tower
|
||
# ~2 GiB pool charge, the 20 GiB host reserve and the host baseline
|
||
# + co-tenancy (frank-secondary, ComfyUI, Caddy/observability) ~15. The
|
||
# box has 121 GiB unified. The n-gram table rides as mmap'd page
|
||
# cache beside the checkpoint and is not a pinned charge (the card's
|
||
# own quickstart arithmetic does not bill it).
|
||
ctx="$(sed -nE 's/^HALOGEN_CTX=([0-9]+)$/\1/p' "$ENV_FILE")"
|
||
slots="$(sed -nE 's/^HALOGEN_KV_SLOTS=([0-9]+)$/\1/p' "$ENV_FILE")"
|
||
pool="$(sed -nE 's/^HALOGEN_KV_POOL_POSITIONS=([0-9]+)$/\1/p' "$ENV_FILE")"
|
||
mt="$(sed -nE 's/^HALOGEN_MAX_TOK=([0-9]+)$/\1/p' "$ENV_FILE")"
|
||
reserve="$(sed -nE 's/^HALOGEN_HOST_RESERVE_GIB=([0-9]+)$/\1/p' "$ENV_FILE")"
|
||
[ "$pool" -eq $(( slots * ctx )) ]
|
||
kv_gib=$(( pool * 28 * 1024 / 1073741824 ))
|
||
arena_tenths=$(( 38 + 84 * mt / 16384 ))
|
||
total_gib=$(( 62 + kv_gib + arena_tenths / 10 + 2 + reserve + 15 ))
|
||
[ "$total_gib" -le 121 ]
|
||
}
|
||
|
||
@test "the serve script refuses when the image is not in storage" {
|
||
podman_stub
|
||
good_env
|
||
run env PATH="$TEST_TMP/bin:$PATH" "${GOOD_ENV[@]}" STUB_DIGESTS="" "$SERVE"
|
||
[ "$status" -ne 0 ]
|
||
[[ "$output" == *"not in podman storage"* ]]
|
||
[[ "$output" == *"podman pull"* ]]
|
||
}
|
||
|
||
@test "the serve script refuses a missing checkpoint and names the fetch script" {
|
||
podman_stub
|
||
good_env
|
||
run env PATH="$TEST_TMP/bin:$PATH" "${GOOD_ENV[@]}" \
|
||
FRANK_LARGE_CHECKPOINT=absent.hgn "$SERVE"
|
||
[ "$status" -ne 0 ]
|
||
[[ "$output" == *"checkpoint"*"missing"* ]]
|
||
[[ "$output" == *"download-frank-large-flashnext.sh"* ]]
|
||
}
|
||
|
||
@test "the serve script refuses a checkpoint of the wrong byte count" {
|
||
# A truncated curl exit-0 artifact must not boot; the Hub's byte
|
||
# count is the contract (fleet fetch law).
|
||
podman_stub
|
||
good_env
|
||
run env PATH="$TEST_TMP/bin:$PATH" "${GOOD_ENV[@]}" \
|
||
FRANK_LARGE_CHECKPOINT_BYTES=42 "$SERVE"
|
||
[ "$status" -ne 0 ]
|
||
[[ "$output" == *"expected 42"* ]]
|
||
}
|
||
|
||
@test "the serve script refuses a missing or wrong-size n-gram table" {
|
||
# The lookup table is REQUIRED: the engine reads it beside the
|
||
# checkpoint (the card names it explicitly), and prompt-lookup
|
||
# drafting dies without it.
|
||
podman_stub
|
||
good_env
|
||
run env PATH="$TEST_TMP/bin:$PATH" "${GOOD_ENV[@]}" \
|
||
FRANK_LARGE_NGRAM_TABLE=absent.hgn "$SERVE"
|
||
[ "$status" -ne 0 ]
|
||
[[ "$output" == *"n-gram-table"*"missing"* ]]
|
||
run env PATH="$TEST_TMP/bin:$PATH" "${GOOD_ENV[@]}" \
|
||
FRANK_LARGE_NGRAM_BYTES=42 "$SERVE"
|
||
[ "$status" -ne 0 ]
|
||
[[ "$output" == *"expected 42"* ]]
|
||
}
|
||
|
||
@test "the serve script refuses a missing or wrong-size vision tower" {
|
||
# Optional on the engine, ENABLED here (image input is a fleet
|
||
# contract) — a silent absence would degrade the endpoint to
|
||
# text-only with no error anywhere.
|
||
podman_stub
|
||
good_env
|
||
run env PATH="$TEST_TMP/bin:$PATH" "${GOOD_ENV[@]}" \
|
||
FRANK_LARGE_VISION_TOWER=absent.hgn "$SERVE"
|
||
[ "$status" -ne 0 ]
|
||
[[ "$output" == *"vision-tower"*"missing"* ]]
|
||
run env PATH="$TEST_TMP/bin:$PATH" "${GOOD_ENV[@]}" \
|
||
FRANK_LARGE_VISION_BYTES=42 "$SERVE"
|
||
[ "$status" -ne 0 ]
|
||
[[ "$output" == *"expected 42"* ]]
|
||
}
|
||
|
||
@test "the serve script refuses a symlinked tokenizer file" {
|
||
# A HuggingFace cache snapshot's entries are symlinks into blobs/ and
|
||
# dangle inside the container mount — even when the directory itself
|
||
# is real.
|
||
podman_stub
|
||
good_env
|
||
rm "$TEST_TMP/tokenizer/tok.json"
|
||
ln -sf /nowhere/x "$TEST_TMP/tokenizer/tok.json"
|
||
run env PATH="$TEST_TMP/bin:$PATH" "${GOOD_ENV[@]}" "$SERVE"
|
||
[ "$status" -ne 0 ]
|
||
[[ "$output" == *"missing or a symlink"* ]]
|
||
}
|
||
|
||
@test "the serve script refuses to start when host RAM is below the pin gate" {
|
||
# The engine's pin gate: MemAvailable must clear the checkpoint plus a
|
||
# 16 GiB floor, or the unit crash-loops (each boot dying in ~5 s) until
|
||
# the RAM clears. The 2026-10-06 cutover hit this — 8 boots, 74.77 GiB
|
||
# vs 78.11 needed. RAM_WAIT=0 so the preflight refuses instead of
|
||
# waiting; the checkpoint is zero bytes (good_env) so the floor is the
|
||
# whole gate.
|
||
podman_stub
|
||
good_env
|
||
printf 'MemTotal: 127108112 kB\nMemAvailable: 10000000 kB\n' > "$TEST_TMP/meminfo-short"
|
||
run env PATH="$TEST_TMP/bin:$PATH" "${GOOD_ENV[@]}" \
|
||
FRANK_LARGE_MEMINFO="$TEST_TMP/meminfo-short" FRANK_LARGE_RAM_WAIT=0 "$SERVE"
|
||
[ "$status" -ne 0 ]
|
||
[[ "$output" == *"pin gate"* ]]
|
||
[[ "$output" == *"refusing to start"* ]]
|
||
}
|
||
|
||
@test "the render names the container, the port map and the engine shape" {
|
||
podman_stub
|
||
good_env
|
||
run env PATH="$TEST_TMP/bin:$PATH" "${GOOD_ENV[@]}" "$SERVE"
|
||
[ "$status" -eq 0 ]
|
||
# `podman run` output is redirected to the log by design (the unit
|
||
# journal must not absorb engine chatter); the stub's printed argv
|
||
# lands there, so the render assertions read the same log.
|
||
output="$output
|
||
$(cat "$TEST_TMP/serve.log")"
|
||
[[ "$output" == *"--name frank-large-halogen"* ]]
|
||
[[ "$output" == *"--publish 7770:8731"* ]]
|
||
[[ "$output" == *"-e HALOGEN_MODEL_ID=frank-large"* ]]
|
||
[[ "$output" == *"-e HALOGEN_CTX=262144"* ]]
|
||
[[ "$output" == *"-e HALOGEN_KV_POOL_POSITIONS=524288"* ]]
|
||
[[ "$output" == *"-e HALOGEN_KV_SLOTS=2"* ]]
|
||
[[ "$output" == *"-e HALOGEN_SPEC_ADAPT=0"* ]]
|
||
[[ "$output" == *"-e HALOGEN_CHECKPOINT=/models/qwen.hgn"* ]]
|
||
[[ "$output" == *"-e HALOGEN_NGRAM_TABLE=/models/ngram.hgn"* ]]
|
||
[[ "$output" == *"-e HALOGEN_VISION_TOWER=/models/vision.hgn"* ]]
|
||
[[ "$output" == *"--device $TEST_TMP/qwen.hgn"* ]]
|
||
[[ "$output" == *"$TEST_TMP/tokenizer:/tokenizer:ro"* ]]
|
||
[[ "$output" == *"ghcr.io/peonist-ai/halogen-flash-server@sha256:cafe"* ]]
|
||
# Foreground run, never -d: the engine ledger must land in the log
|
||
# file (`podman run -d` captured only the container ID and the
|
||
# runbook's ledger grep read a one-line hex file, found 2026-10-06).
|
||
! grep -qE '(^|[[:space:]])-d([[:space:]]|$)' "$TEST_TMP/serve.log"
|
||
! grep -q 'PODMAN wait' "$TEST_TMP/serve.log"
|
||
}
|
||
|
||
@test "the shipped env keeps the harness fit law inside the ceiling" {
|
||
# 262144 (the checkpoint's native window) is the per-slot hard ceiling
|
||
# (a longer prompt is a 400 naming the limit, never a silent
|
||
# truncation). The harness clamps max_tokens = min(45056, 217088 − est
|
||
# − 4096), compacts at 85 % of its declared 217088 window, and its
|
||
# chars/4 est UNDER-counts the rendered prompt by ~3 % on code/agent
|
||
# traffic (measured 4,450 tokens at est 152,938 on 2026-10-07 — with
|
||
# window == ceiling, every request over ~146k est was a guaranteed
|
||
# 400 before compaction could fire at 85 %). The 45k gap between the
|
||
# harness window and the engine ceiling must absorb that error at
|
||
# both monotone maxima of est + budget (est ≤ 217088 − 4096):
|
||
# full budget at the compaction threshold: 1.03*184524 + 45056
|
||
# clamped budget at the clamp's zero point: 1.03*212992 + 0
|
||
# and the compaction request that rides on frank-secondary (its
|
||
# 200,704-token slot) must fit: input ≈ threshold − keepRecent(20k).
|
||
grep -qE '^HALOGEN_CTX=262144$' "$ENV_FILE"
|
||
ctx=262144
|
||
hw=217088; mt=45056
|
||
thr=$(( hw * 85 / 100 ))
|
||
[ $(( thr * 103 / 100 + mt )) -le "$ctx" ]
|
||
zero=$(( hw - 4096 ))
|
||
[ $(( zero * 103 / 100 )) -le "$ctx" ]
|
||
[ $(( (thr - 20000) * 103 / 100 )) -le 200704 ]
|
||
}
|
||
|
||
@test "no HIP-sensitive bare names leak through the env file" {
|
||
# HIP reads bare env vars out of a `set -a` source; a tunable named
|
||
# HOST or TEMP used to send the JIT cache to path 1.0 and segfault
|
||
# every load (kept from the llama.cpp era — the container gets only
|
||
# the explicit -e list, but the host env still reaches podman itself).
|
||
! grep -qE '^(HOST|TEMP|GPU_MAX_HEAP_SIZE)=' "$ENV_FILE"
|
||
}
|
||
|
||
@test "the deployer gates exactly the artifacts the serve script opens" {
|
||
# Serve and deploy must name the SAME image digest, checkpoint and
|
||
# tokenizer: the 2026-10-01 crash-loop was exactly these twins
|
||
# disagreeing mid-cutover.
|
||
img="$(sed -nE 's/^FRANK_LARGE_IMAGE=(.*)$/\1/p' "$ENV_FILE")"
|
||
grep -qF "LLM_LARGE_IMAGE=\"\${LLM_LARGE_IMAGE:-$img}\"" "$DEPLOYER"
|
||
dir="$(sed -nE 's/^FRANK_LARGE_MODEL_DIR=(.*)$/\1/p' "$ENV_FILE")"
|
||
ckpt="$(sed -nE 's/^FRANK_LARGE_CHECKPOINT=(.*)$/\1/p' "$ENV_FILE")"
|
||
tokf="$(sed -nE 's/^FRANK_LARGE_TOKENIZER_FILES=\"(.*)\"$/\1/p' "$ENV_FILE")"
|
||
grep -qF "LLM_LARGE_TOK_DIR=\"\${LLM_LARGE_TOK_DIR:-$dir/tokenizer}\"" "$DEPLOYER"
|
||
grep -qF "LLM_LARGE_TOK_FILES=\"\${LLM_LARGE_TOK_FILES:-$tokf}\"" "$DEPLOYER"
|
||
bytes="$(sed -nE 's/^FRANK_LARGE_CHECKPOINT_BYTES=([0-9]+)$/\1/p' "$ENV_FILE")"
|
||
grep -qF "LLM_LARGE_CKPT_BYTES=\"\${LLM_LARGE_CKPT_BYTES:-$bytes}\"" "$DEPLOYER"
|
||
}
|
||
|
||
@test "the deployer points a missing artifact at the flashnext fetch script" {
|
||
grep -qE 'download-frank-large-flashnext\.sh' "$DEPLOYER"
|
||
grep -qE 'podman pull' "$DEPLOYER"
|
||
}
|
||
|
||
@test "the stray sweep cannot take frank-secondary or the deployer down" {
|
||
# frank-secondary also listens on this host (7771, llama-server) and the
|
||
# deployer's own command line contains "frank-large"; only the FULL
|
||
# container name matches a stray manual flash-server run and nothing
|
||
# else.
|
||
grep -q "pkill -f 'frank-large-halogen'" "$DEPLOYER"
|
||
! grep -qE "pkill -f 'llama-server'" "$DEPLOYER"
|
||
! grep -qE "pkill -f 'frank-large'" "$DEPLOYER"
|
||
}
|
||
|
||
@test "the deployed unit keeps the fleet's restart and boot-persistence shape" {
|
||
grep -qE '^Restart=(always|on-failure)$' "$UNIT"
|
||
grep -qE '^WantedBy=' "$UNIT"
|
||
grep -qE '^ExecStart=.*/serve-frank-large\.sh$' "$UNIT"
|
||
grep -qE '^User=dank$' "$UNIT"
|
||
grep -qE '^LimitMEMLOCK=infinity$' "$UNIT"
|
||
# The service's lifetime is the container's; stopping the service
|
||
# must stop the container by its real name.
|
||
grep -qE '^ExecStop=.*podman stop .* frank-large-halogen$' "$UNIT"
|
||
}
|
||
|
||
@test "the unit runs the flash-server runtime and no retired path" {
|
||
grep -q 'halogen-flash-server' "$UNIT"
|
||
# Every retired payload/build stays on the host, so a stale path in
|
||
# a unit still resolves — to a runtime nobody has measured in weeks.
|
||
! grep -qE 'GitPackages/(ROCmFPX-kairic|llama.cpp-ik_llama|llama-builds|ciru-orca)' "$UNIT"
|
||
! grep -qE 'kingjones-ROCmFPX' "$UNIT"
|
||
}
|
||
|
||
@test "the rollback door stays qualified: the ROCmFPX build pin survives" {
|
||
# Rolling back to the pre-halogen shape means rebuilding the fork the
|
||
# old payload needs; the pin (real commit, gfx1151, no webui fetch)
|
||
# is what makes that door trustworthy months later.
|
||
grep -qE 'ROCMFPX_COMMIT=.*[0-9a-f]{40}' "$BUILD"
|
||
grep -qE 'GPU_TARGET=.*gfx1151' "$BUILD"
|
||
grep -qE 'DLLAMA_BUILD_WEBUI=OFF' "$BUILD"
|
||
}
|