serverAppConfigs/tests/frank_small_unit.bats

#!/usr/bin/env bats
# Seam: the frank-small llama.cpp root unit on dankclaw.
# frank-small is the RTX 3090 endpoint; since 2026-10-01 night it serves
# bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q6_K via a CUDA (sm_86) build of
# llama.cpp master, chosen because it is the only runtime here that moves K and
# V independently. Since 2026-10-03 it runs TWO unquantized contexts of
# 200,704 tokens each and carries a vision projector, and the card must keep
# 2-3 GiB free. This seam runs the serve script against a stub engine and
# asserts on the argv it actually execs, so what is pinned is the
# command the operator gets.

load helpers

UNIT="$REPO_ROOT/scripts/frank-small.service"
SERVE="$REPO_ROOT/scripts/serve-frank-small.sh"
ENV_FILE="$REPO_ROOT/scripts/frank-small.env"
REMOTE_DEPLOY="$REPO_ROOT/scripts/deploy-remote.sh"
ENV_LARGE="$REPO_ROOT/scripts/frank-large.env"
TARGET_STUB="MiMo-V2.6-Distill-Qwen-9B-Q6_K.gguf"
# Same basename as the shipped projector: the test env repoints it into $STAGE.
MM_STUB="mmproj-MiMo-V2.6-Distill-Qwen-9B-f16.gguf"

setup() {
    STAGE="$(mktemp -d)"
    RUNTIME_DIR="$STAGE/llama"
    MODEL_DIR="$STAGE/models"
    mkdir -p "$RUNTIME_DIR/bin" "$MODEL_DIR"
    cat > "$RUNTIME_DIR/bin/llama-server" <<'STUB'
#!/usr/bin/env bash
printf '%s\n' "$@"
STUB
    chmod +x "$RUNTIME_DIR/bin/llama-server" "$RUNTIME_DIR/bin" 2>/dev/null || chmod +x "$RUNTIME_DIR/bin/llama-server"
    touch "$MODEL_DIR/$TARGET_STUB" "$MODEL_DIR/$MM_STUB"
}

teardown() {
    rm -rf "$STAGE"
}

# serve_argv [env-file] — run the serve script and capture the engine's
# argv, one token per line, in $output.
serve_argv() {
    local envf="${1:-$STAGE/test.env}"
    local mmproj
    mmproj="$(sed -nE 's/^MMPROJ_FILE=(.+)$/\1/p' "$ENV_FILE")"
    cat > "$envf" <<EOF
LLAMA_BIN=$RUNTIME_DIR/bin/llama-server
MODEL_FILE=$MODEL_DIR/$TARGET_STUB
MMPROJ_FILE=$MODEL_DIR/${mmproj##*/}
ALIAS=frank-small
BIND_ADDR=0.0.0.0
LISTEN_PORT=7771
CTX_SIZE=$(sed -nE 's/^CTX_SIZE=([0-9]+)$/\1/p' "$ENV_FILE")
PARALLEL=$(sed -nE 's/^PARALLEL=([0-9]+)$/\1/p' "$ENV_FILE")
CACHE_TYPE_K=$(sed -nE 's/^CACHE_TYPE_K=(.+)$/\1/p' "$ENV_FILE")
CACHE_TYPE_V=$(sed -nE 's/^CACHE_TYPE_V=(.+)$/\1/p' "$ENV_FILE")
NGL=$(sed -nE 's/^NGL=([0-9]+)$/\1/p' "$ENV_FILE")
EOF
    run env FRANK_SMALL_ENV_FILE="$envf" nvidia-modprobe=true bash "$SERVE"
}

argv_value() {
    grep -A1 -xF -- "$1" <<<"$output" | tail -1
}

@test "frank-small unit, serve script and env exist in scripts/" {
    [ -f "$UNIT" ]
    [ -f "$SERVE" ]
    [ -f "$ENV_FILE" ]
}

@test "frank-small is boot-persistent, self-healing and unprivileged" {
    grep -q '^WantedBy=multi-user.target$' "$UNIT"
    grep -q '^Restart=on-failure$' "$UNIT"
    grep -q '^RestartSec=' "$UNIT"
    grep -q '^User=dank$' "$UNIT"
    grep -q '^LimitMEMLOCK=infinity$' "$UNIT"
    grep -q '^ExecStart=/home/dank/serverAppConfigs/scripts/serve-frank-small.sh$' "$UNIT"
    grep -q 'FRANK_SMALL_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-small.env' "$UNIT"
}

@test "the shipped env points at the llama.cpp runtime and the Q6_K GGUF" {
    grep -qE '^LLAMA_BIN=/home/dank/GitPackages/llama-master/build-cuda/bin/llama-server$' "$ENV_FILE"
    grep -qE "^MODEL_FILE=/home/dank/models/MiMo-Q6K/$TARGET_STUB$" "$ENV_FILE"
}

@test "the deployer gates on exactly the payload paths the env file ships" {
    # Anti-drift: the deploy handler checks files by its own defaults. If
    # those ever differ from what the unit actually loads, a green deploy
    # would be gating on a file nobody reads — and a missing projector would
    # ship a blind endpoint.
    local env_v dep_v path pair
    for pair in "MODEL_FILE LLM_SMALL_MODEL_FILE" "MMPROJ_FILE LLM_SMALL_MMPROJ"; do
        read -r env_v dep_v <<<"$pair"
        path="$(sed -nE "s/^${env_v}=(.+)\$/\1/p" "$ENV_FILE" | tail -1)"
        [ -n "$path" ]
        grep -qF -- "${dep_v}=\"\${${dep_v}:-${path}}\"" "$REMOTE_DEPLOY"
    done
}

@test "the shipped env serves the fleet shape: two 200704-token contexts" {
    serve_argv
    [ "$status" -eq 0 ]
    [ "$(argv_value --alias)" = "frank-small" ]
    [ "$(argv_value --port)" = "7771" ]
    [ "$(argv_value --host)" = "0.0.0.0" ]
    [ "$(argv_value --model)" = "$MODEL_DIR/$TARGET_STUB" ]
    [ "$(argv_value --n-gpu-layers)" -gt 0 ]
    # llama.cpp divides --ctx-size across slots and a mamba hybrid cannot
    # share one cache, so the observable contract is the per-slot window.
    [ "$(argv_value --parallel)" -eq 2 ]
    ctx="$(argv_value --ctx-size)"
    par="$(argv_value --parallel)"
    [ $((ctx % par)) -eq 0 ]
    [ $((ctx / par)) -eq 200704 ]
    [ $((ctx / par)) -le 262144 ]
}

@test "the KV contract is unquantized both halves, flash-attn on" {
    serve_argv
    [ "$status" -eq 0 ]
    [ "$(argv_value --cache-type-k)" = "f16" ]
    # Frank, 2026-10-03: the values are unquantized too. The flag pair is what
    # makes this observable — a build without the FA path silently falls back,
    # so both must appear in the argv the supervisor runs.
    [ "$(argv_value --cache-type-v)" = "f16" ]
    [ "$(argv_value --flash-attn)" = "on" ]
}

@test "the KV budget leaves 2-3 GiB of the 3090 free" {
    # Rate, from the GGUF geometry: 8 full-attention layers x 4 kv heads x
    # 256 dim x 2 B = 16 KiB/token for K and the same for V => 32 KiB/token
    # (budgeted 33 with slack). The non-KV half is MEASURED on this card on
    # 2026-10-02: with the projector loaded the engine reported 22,972 MiB
    # used against 14,113 MiB of KV, so weights + vision tower + DeltaNet
    # state + compute buffers + CUDA graphs = 8,859 MiB => 9 GiB. Two asserts,
    # both about the output the operator sees: the pool must still fit with
    # 2 GiB spare, and it must be large enough that 5 GiB spare is NOT
    # reachable (an undersized pool is as wrong as an oversized one).
    # Arithmetic, not a boot log: change CTX_SIZE and this bites before the
    # deploy does. The same pool with the OLD 24.5 KiB/token rate would leave
    # ~6 GiB free — i.e. the unquantized V is what puts this shape in the band.
    ctx="$(sed -nE 's/^CTX_SIZE=([0-9]+)$/\1/p' "$ENV_FILE")"
    kv_gib=$((ctx * 33 / 1048576))
    [ $((kv_gib + 9 + 2)) -le 24 ]
    [ $((kv_gib + 9 + 5)) -gt 24 ]
    # And the ceiling that sets the per-slot window: two NATIVE windows cannot
    # be paid for in full precision on this card.
    native=$((2 * 262144))
    [ $((native * 33 / 1048576 + 9)) -gt 24 ]
}

@test "the compute-buffer pair is explicit" {
    # This endpoint ran on llama.cpp's own defaults until 2026-10-03; the
    # fleet now pins 2048/1024 so the number a benchmark attributes the
    # prefill rate to is a repo value, not an engine default nobody wrote down.
    serve_argv
    [ "$status" -eq 0 ]
    [ "$(argv_value --batch-size)" = "2048" ]
    [ "$(argv_value --ubatch-size)" = "1024" ]
}

@test "no speculative draft ships by default" {
    # The qwen35 GGUF has no MTP tensors, and the cross-model DFlash draft
    # is a measured decision the harness makes later, not a default.
    ! grep -q -- '--model-draft' "$SERVE"
    ! grep -q -- '--spec-type' "$SERVE"
    ! grep -q '^DRAFT' "$ENV_FILE"
}

@test "vision ships by default and MMPROJ_FILE empty opts out of the image path" {
    # The Q6_K GGUF carries no `v.*` tensors, so the projector argument IS
    # the vision capability: no flag, no eyes.
    serve_argv
    [ "$status" -eq 0 ]
    [ "$(argv_value --mmproj)" = "$MODEL_DIR/$MM_STUB" ]

    # The documented opt-out must reach the engine as ABSENCE of the flag,
    # not as an argument pointing at an empty string.
    sed -i 's|^MMPROJ_FILE=.*|MMPROJ_FILE=|' "$STAGE/test.env"
    run env FRANK_SMALL_ENV_FILE="$STAGE/test.env" nvidia-modprobe=true bash "$SERVE"
    [ "$status" -eq 0 ]
    ! grep -qxF -- '--mmproj' <<<"$output"
}

@test "the fleet reasoning contract survives the reslice to two wide contexts" {
    serve_argv
    [ "$status" -eq 0 ]
    # deepseek format = thinking lands in reasoning_content, the field the
    # harness reads on this endpoint; --jinja is what makes
    # chat_template_kwargs reach the template at all.
    [ "$(argv_value --reasoning-format)" = "deepseek" ]
    argv_value --jinja >/dev/null
    grep -qxF -- '--jinja' <<<"$output"
}

@test "the serve script refuses a missing runtime, GGUF or projector" {
    rm -f "$MODEL_DIR/$MM_STUB"
    serve_argv
    [ "$status" -ne 0 ]
    [[ "$output" == *"frank-small: missing"* ]]

    rm -f "$RUNTIME_DIR/bin/llama-server"
    serve_argv
    [ "$status" -ne 0 ]
    [[ "$output" == *"frank-small: missing"* ]]
}

@test "the deploy handler gates on binary, GGUF and projector, then MainPID-hardens health" {
    grep -q 'deploy_llm_small' "$REMOTE_DEPLOY"
    grep -q 'LLM_SMALL_RUNTIME' "$REMOTE_DEPLOY"
    grep -q 'LLM_SMALL_MODEL_FILE' "$REMOTE_DEPLOY"
    grep -q 'LLM_SMALL_MMPROJ' "$REMOTE_DEPLOY"
    grep -q 'relink_unit frank-small' "$REMOTE_DEPLOY"
    grep -q 'systemctl enable frank-small.service' "$REMOTE_DEPLOY"
    grep -q '127.0.0.1:7771/health' "$REMOTE_DEPLOY"
    grep -q 'frank-small.service has no MainPID' "$REMOTE_DEPLOY"
}

@test "the two endpoints keep separate ports and the large handler never pkills llama-server" {
    # frank-large's gufo sweep must not take down frank-small, whose
    # process is llama-server on the SAME host since this swap.
    grep -q '^LISTEN_PORT=7771$' "$ENV_FILE"
    local large
    large="$(sed -n '/^deploy_llm_large() {/,/^}/p' "$REMOTE_DEPLOY")"
    ! grep -q 'pkill -x llama-server' <<<"$large"
}