serverAppConfigs/tests/frank_secondary_unit.bats

# Seam: the frank-secondary llama.cpp root unit on dankclaw.
# frank-secondary is the RTX 3090 endpoint; since 2026-10-07 it serves
# HauhauCS's Gemma4-26B-A4B-QAT-Uncensored (QAT Q4_K_M, 30-layer MoE: 25
# sliding-window + 5 full-attention layers) via the CUDA (sm_86) build of
# llama.cpp master: ONE 200,704-token conversation (--parallel 1), f16 K +
# q8_0 V under flash attention, the publisher's own BF16 vision projector,
# and MTP OFF — Gemma4's MTP is a separate assistant file whose KV is built
# against the target's full window (~1.9 GiB measured), which the f16-K raise
# cannot afford on a 24 GiB card. Log verbosity 4 ships so the VRAM-fit
# forensics (KV layout, buffer sizes, graph capture) land in the journal.
# 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="$REPO_ROOT/scripts/frank-secondary.service"
SERVE="$REPO_ROOT/scripts/serve-frank-secondary.sh"
ENV_FILE="$REPO_ROOT/scripts/frank-secondary.env"
REMOTE_DEPLOY="$REPO_ROOT/scripts/deploy-remote.sh"
ENV_LARGE="$REPO_ROOT/scripts/frank-large.env"

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"
    # The stub payload files carry the SAME basenames as the shipped env, so
    # the seam exercises the real paths, and a payload rename moves one file
    # (the env) instead of silently forking the test's filename constants.
    MODEL_STUB="$(basename "$(sed -nE 's/^MODEL_FILE=(.+)$/\1/p' "$ENV_FILE")")"
    MM_STUB="$(basename "$(sed -nE 's/^MMPROJ_FILE=(.+)$/\1/p' "$ENV_FILE")")"
    DRAFT_STUB="mtp-gemma-4-26B-A4B-it.gguf"
    touch "$MODEL_DIR/$MODEL_STUB" "$MODEL_DIR/$MM_STUB" "$MODEL_DIR/$DRAFT_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:-$STAGE/test.env}"
    cat > "$envf" <<EOF
LLAMA_BIN=$RUNTIME_DIR/bin/llama-server
MODEL_FILE=$MODEL_DIR/$MODEL_STUB
MMPROJ_FILE=$MODEL_DIR/$MM_STUB
ALIAS=frank-secondary
BIND_ADDR=0.0.0.0
LISTEN_PORT=7771
CTX_SIZE=$(sed -nE 's/^CTX_SIZE=([0-9]+)$/\1/p' "$ENV_FILE")
PARALLEL=$(sed -nE 's/^PARALLEL=([0-9]+)$/\1/p' "$ENV_FILE")
BATCH_SIZE=$(sed -nE 's/^BATCH_SIZE=([0-9]+)$/\1/p' "$ENV_FILE")
UBATCH_SIZE=$(sed -nE 's/^UBATCH_SIZE=([0-9]+)$/\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' "$ENV_FILE")
SPEC_TYPE=$(sed -nE 's/^SPEC_TYPE=(.+)$/\1/p' "$ENV_FILE")
SPEC_DRAFT_N_MAX=$(sed -nE 's/^SPEC_DRAFT_N_MAX=([0-9]+)$/\1/p' "$ENV_FILE")
VERBOSITY=$(sed -nE 's/^VERBOSITY=([0-9]+)$/\1/p' "$ENV_FILE")
NGL=$(sed -nE 's/^NGL=([0-9]+)$/\1/p' "$ENV_FILE")
EOF
    run env FRANK_SECONDARY_ENV_FILE="$envf" nvidia-modprobe=true bash "$SERVE"
}

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

# run_stage — exec the CURRENT $STAGE/test.env as-is. serve_argv REWRITES
# that file from the shipped env, so any test that mutates it (drop a line,
# append a drafter) must exec through this, not serve_argv — which silently
# undoes the mutation and makes the assertion a tautology.
run_stage() {
    run env FRANK_SECONDARY_ENV_FILE="$STAGE/test.env" nvidia-modprobe=true bash "$SERVE"
}

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

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

@test "the shipped env points at the llama.cpp runtime and the Gemma4-26B-A4B QAT Q4_K_M GGUF" {
    # The payload path IS the endpoint's identity.
    grep -qE '^LLAMA_BIN=/home/dank/GitPackages/llama-master/build-cuda/bin/llama-server$' "$ENV_FILE"
    grep -qE '^MODEL_FILE=/home/dank/models/Gemma4-26B-A4B/Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-Q4_K_M\.gguf$' "$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_SECONDARY_MODEL_FILE" "MMPROJ_FILE LLM_SECONDARY_MMPROJ"; do
        env_v="${pair%% *}"
        dep_v="${pair##* }"
        path="$(sed -nE "s/^${env_v}=(.+)$/\1/p" "$ENV_FILE")"
        grep -qF -- "${dep_v}=\"\${${dep_v}:-${path}}\"" "$REMOTE_DEPLOY"
    done
}

@test "one conversation owns the whole 200704 window" {
    serve_argv
    [ "$status" -eq 0 ]
    [ "$(argv_value --alias)" = "frank-secondary" ]
    [ "$(argv_value --port)" = "7771" ]
    [ "$(argv_value --host)" = "0.0.0.0" ]
    [ "$(argv_value --model)" = "$MODEL_DIR/$MODEL_STUB" ]
    [ "$(argv_value --n-gpu-layers)" -gt 0 ]
    # llama.cpp divides --ctx-size across slots, so the observable contract
    # is the per-slot window. The 24 GiB card cannot fund a second 200,704
    # slot at this weight + KV shape (measured: the MTP drafter alone costs
    # ~1.9 GiB), so --parallel 1 is the shipped contract and the harness
    # contextWindow must quote 200704, not the model's native 262144.
    [ "$(argv_value --parallel)" -eq 1 ]
    [ "$(argv_value --ctx-size)" -eq 200704 ]
}

@test "the KV contract is f16 K + q8_0 V, flash-attn on" {
    serve_argv
    [ "$status" -eq 0 ]
    # Frank, 2026-10-07: K raised to f16 (exact), V stays q8_0 — llama.cpp's
    # FP8 class (1.0625 B/elem; no true fp8 KV dtype exists). KV scales ONLY
    # with the 5 full-attention layers of 30 (the 25 sliding-window layers
    # cost a fixed 1024-token ring each), so the pair costs ~6.2 GiB at
    # 200,704 — the boot ledger, not this file, is the referee. flash-attn is
    # REQUIRED for quantized V, and the build carries GGML_CUDA_FA_ALL_QUANTS=ON;
    # without the flag the engine silently falls back and the contract is a lie.
    [ "$(argv_value --cache-type-k)" = "f16" ]
    [ "$(argv_value --cache-type-v)" = "q8_0" ]
    [ "$(argv_value --flash-attn)" = "on" ]
}

@test "log verbosity follows the env file" {
    serve_argv
    [ "$status" -eq 0 ]
    # The shipped 4 (debug) is what makes VRAM-fit forensics possible from
    # the journal (KV layout, buffer sizes, graph capture).
    [ "$(argv_value --log-verbosity)" = "4" ]

    # And an env that names no verbosity still ships the engine default
    # explicitly — the script's written-down 3, never a blank.
    sed -i '/^VERBOSITY=/d' "$STAGE/test.env"
    run_stage
    [ "$status" -eq 0 ]
    [ "$(argv_value --log-verbosity)" = "3" ]
}

@test "the compute-buffer pair follows the env file and stays self-consistent" {
    # The contract is: whatever rung the repo carries is the rung the engine
    # is exec'd with — the number a benchmark attributes a prefill rate to
    # must be a repo value, never an engine default nobody wrote down.
    # Asserted against the env rather than a literal so a retune moves one
    # file, not two.
    local env_batch env_ubatch
    env_batch="$(sed -nE 's/^BATCH_SIZE=([0-9]+)$/\1/p' "$ENV_FILE")"
    env_ubatch="$(sed -nE 's/^UBATCH_SIZE=([0-9]+)$/\1/p' "$ENV_FILE")"
    serve_argv
    [ "$status" -eq 0 ]
    [ "$(argv_value --batch-size)" = "$env_batch" ]
    [ "$(argv_value --ubatch-size)" = "$env_ubatch" ]
    # llama.cpp refuses ubatch > batch, so a retune that inverts the pair has
    # to fail here instead of at boot on a live endpoint.
    [ "$env_batch" -ge "$env_ubatch" ]

    # And an env that names neither flag still ships an explicit pair: the
    # serve script's fallbacks are written-down values, not blanks the engine
    # fills in silently.
    sed -i '/^BATCH_SIZE=/d;/^UBATCH_SIZE=/d' "$STAGE/test.env"
    run_stage
    [ "$status" -eq 0 ]
    argv_value --batch-size | grep -qE '^[0-9]+$'
    argv_value --ubatch-size | grep -qE '^[0-9]+$'
}

@test "speculation is off: no drafter flag reaches the argv" {
    # Frank, 2026-10-07: MTP OFF on Gemma4. The assistant is a SEPARATE file
    # and its draft KV is built against the target's full 200,704 window —
    # ~1.9 GiB measured (23,806/319 free), a knife-edge once K is f16. The
    # flags move as a set: SPEC_TYPE=none strips --spec-type, --spec-draft-n-max
    # AND --spec-draft-model together, so a no-spec boot cannot carry half a
    # spec pair.
    serve_argv
    [ "$status" -eq 0 ]
    ! grep -qxF -- '--spec-type' <<<"$output"
    ! grep -qxF -- '--spec-draft-n-max' <<<"$output"
    ! grep -qxF -- '--spec-draft-model' <<<"$output"
    grep -qE '^SPEC_TYPE=none$' "$ENV_FILE"
}

@test "naming a drafter ships the full MTP trio" {
    # The opt-back-in path: SPEC_TYPE + SPEC_DRAFT_FILE (the separate
    # gemma4-assistant gguf) must reach the engine as a complete set — a
    # draft-mtp flag without its model file boots a drafter against the main
    # weights and drafts nothing on this architecture.
    serve_argv
    {
        echo 'SPEC_TYPE=draft-mtp'
        echo 'SPEC_DRAFT_N_MAX=3'
        echo "SPEC_DRAFT_FILE=$MODEL_DIR/$DRAFT_STUB"
    } >> "$STAGE/test.env"
    run_stage
    [ "$(argv_value --spec-type)" = "draft-mtp" ]
    [ "$(argv_value --spec-draft-n-max)" = "3" ]
    [ "$(argv_value --spec-draft-model)" = "$MODEL_DIR/$DRAFT_STUB" ]
}

@test "vision ships by default and MMPROJ_FILE empty opts out of the image path" {
    # The Gemma4 GGUF carries no vision 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=|' "$STAGE/test.env"
    run env FRANK_SECONDARY_ENV_FILE="$STAGE/test.env" nvidia-modprobe=true bash "$SERVE"
    [ "$status" -eq 0 ]
    ! grep -qxF -- '--mmproj' <<<"$output"
}

@test "the fleet reasoning contract reaches the argv" {
    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-secondary: missing"* ]]

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

@test "the deploy handler gates on binary, GGUF and projector, then MainPID-hardens health" {
    grep -q 'deploy_llm_secondary' "$REMOTE_DEPLOY"
    grep -q 'LLM_SECONDARY_RUNTIME' "$REMOTE_DEPLOY"
    grep -q 'LLM_SECONDARY_MODEL_FILE' "$REMOTE_DEPLOY"
    grep -q 'LLM_SECONDARY_MMPROJ' "$REMOTE_DEPLOY"
    grep -q 'relink_unit frank-secondary' "$REMOTE_DEPLOY"
    grep -q 'systemctl enable frank-secondary.service' "$REMOTE_DEPLOY"
    grep -q '127.0.0.1:7771/health' "$REMOTE_DEPLOY"
    grep -q 'frank-secondary.service has no MainPID' "$REMOTE_DEPLOY"
}

@test "the two endpoints keep separate ports and the large handler never pkills llama-server" {
    # frank-large's sweeps must not take down frank-secondary, whose
    # process is llama-server on the SAME host.
    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"
}