serverAppConfigs/tests/frank_primary_unit.bats

#!/usr/bin/env bats
# Seam: frank-primary — the Dankserver LLM endpoint on :7770.
#
# This file asserts the llama.cpp ROOT-UNIT shape (the 2026-09-26 swap that
# replaced the Lucebox DS4.1 Quadlet): the unsloth b11030-mix prebuilt on
# the two R9700s (gfx1201) serving unsloth/Qwen3.8-Flash-Next-GGUF at Q8_0
# with the shared Q8_0 MTP head, the BF16 projector, and the
# draft-mtp + ngram-mod chain. The seam pins what the flags alone do not
# say: the CPU-override placement law (experts and the 51B n-gram table
# are COMPUTED in host RAM, never streamed), mmap staying on, the
# shared-head borrow requirement (per_layer_token_embd on CPU), the
# explicit projector (never autoloaded by this build), HIP env hygiene,
# and the deployer's byte-count gates over a six-part payload.

load helpers

UNIT="$REPO_ROOT/scripts/frank-primary.service"
SERVE="$REPO_ROOT/scripts/serve-frank-primary.sh"
ENV_FILE="$REPO_ROOT/scripts/frank-primary.env"
REMOTE_DEPLOY="$REPO_ROOT/scripts/deploy-remote.sh"

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

@test "frank-primary is boot-persistent, self-healing and unprivileged" {
    # Root unit parity with frank-large/frank-small: enable is the [Install]
    # section, the restart policy survives a crash, and the mmap'd payload
    # needs an unbounded memlock.
    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"
}

@test "frank-primary runs the repo's own serve script with the repo's env" {
    grep -q '^ExecStart=/home/dank/serverAppConfigs/scripts/serve-frank-primary.sh$' "$UNIT"
    grep -q 'FRANK_PRIMARY_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-primary.env' "$UNIT"
}

@test "frank-primary drafts with the shared MTP head chained behind ngram-mod" {
    # The chain is draft-mtp (context-backed) + ngram-mod (draftless): the
    # only legal way to layer two spec implementations in one process. The
    # shared Q8_0 head borrows the target's embedding tensors — which is
    # why per_layer_token_embd.weight must be CPU-resident (a GPU-resident
    # borrow crashes the draft load with "invalid vector subscript").
    grep -q -- '--spec-type draft-mtp,ngram-mod' "$SERVE"
    grep -q '^SPEC_DRAFT_N_MAX=2$' "$ENV_FILE"
    grep -q -- '--spec-draft-n-max "$SPEC_DRAFT_N_MAX"' "$SERVE"
    grep -q 'DRAFTER_FILE="$MODEL_ROOT/MTP/mtp-Qwen3.8-Flash-Next-shared-Q8_0.gguf"' "$SERVE"
    grep -q -- '--spec-draft-device "$SPEC_DRAFT_DEVICE"' "$SERVE"
}

@test "the bandwidth-huge tensors are computed in host RAM, not streamed" {
    # The x4-pair law: streaming experts over PCIe loses (3.7 tok/s) while
    # computing them in RAM does not care (20+ tok/s on the same model
    # shape). exps=CPU plus the n-gram embedding table on CPU; the PLE
    # table must NEVER carry a GPU target (the 23 -> 13.4 t/s regression).
    grep -q '^OT_OVERRIDES=exps=CPU,ngram_embeddings=CPU,per_layer_token_embd.weight=CPU$' "$ENV_FILE"
    grep -q -- '--override-tensor "$ot"' "$SERVE"
    # ...and mmap must stay on: --no-mmap forces the 51B-param table into
    # anonymous memory and the cgroup kill is silent.
    ! grep -q -- '--no-mmap' "$SERVE"
    ! grep -q '^MMPROJ_ON_GPU' "$ENV_FILE"
}

@test "the projector is explicit, never autoloaded" {
    # This build never autoloads mmproj from the model directory: without
    # the flag the server comes up healthy and text-only, answering image
    # requests with 500 (the frank-medium 2026-09-17 trap).
    grep -q -- '--mmproj "$MMPROJ_FILE"' "$SERVE"
    grep -q 'MMPROJ_FILE="$MODEL_ROOT/mmproj-BF16.gguf"' "$SERVE"
}

@test "frank-primary is vision-serving but holds the single fleet port" {
    grep -q '^PORT=7770$' "$ENV_FILE"
    grep -q '^BIND_HOST=0.0.0.0$' "$ENV_FILE"
    grep -q -- '--alias frank-primary' "$SERVE"
    grep -q -- '--host "$BIND_HOST"' "$SERVE"
    grep -q -- '--port "$PORT"' "$SERVE"
}

@test "one stream, the model's full native window" {
    local ctx parallel
    ctx="$(sed -nE 's/^CONTEXT_SIZE=([0-9]+)$/\1/p' "$ENV_FILE")"
    parallel="$(sed -nE 's/^PARALLEL_SLOTS=([0-9]+)$/\1/p' "$ENV_FILE")"
    [ -n "$ctx" ] && [ -n "$parallel" ]
    [ "$ctx" -eq 262144 ]
    [ "$parallel" -eq 1 ]
    grep -q -- '--ctx-size "$CONTEXT_SIZE"' "$SERVE"
    grep -q -- '--parallel "$PARALLEL_SLOTS"' "$SERVE"
}

@test "reasoning is extracted to reasoning_content and tools are legal" {
    # The harness contract: llama.cpp endpoints emit reasoning_content
    # (the deepseek format is the one that fills it), and tools require
    # --jinja (the ik_llama 500 lesson). The Qwen3.8 template gates
    # reasoning_effort to {xhigh, medium, low} — folded in models.yml.
    grep -q -- '--jinja' "$SERVE"
    grep -q -- '--reasoning auto' "$SERVE"
    grep -q -- '--reasoning-format deepseek' "$SERVE"
    grep -q -- '--reasoning-budget -1' "$SERVE"
}

@test "the greedy server default is explicit" {
    # Deterministic e2e probes; the harness overrides sampling per request.
    grep -q -- '--temp 0' "$SERVE"
    grep -q -- '--top-p 1.0' "$SERVE"
    grep -q -- '--top-k 0' "$SERVE"
    grep -q -- '--min-p 0.0' "$SERVE"
}

@test "both R9700s are visible and the Raphael iGPU is not" {
    # The host has a third (Raphael) GPU the server must never place
    # tensors on; the bundled ROCm runtime is the only one linked.
    grep -q 'export HIP_VISIBLE_DEVICES=0,1$' "$SERVE"
    grep -q 'export LD_LIBRARY_PATH="$RUNTIME_DIR' "$SERVE"
}

@test "no bare HIP-reserved env var is defined" {
    # HIP reads bare TEMP for its JIT cache path (2026-08-13: TEMP=1.0
    # segfaulted every load), and HOST/GPU_MAX_HEAP_SIZE are the same
    # class. The bind address is BIND_HOST, not HOST.
    ! grep -qE '^(TEMP|HOST|GPU_MAX_HEAP_SIZE)=' "$ENV_FILE"
    grep -q '^BIND_HOST=' "$ENV_FILE"
    ! grep -qE '^(export )?(TEMP|HOST|GPU_MAX_HEAP_SIZE)=' "$SERVE"
}

@test "the serve script refuses to start on a half-finished download" {
    # Six split parts plus the head and the projector: a missing tail part
    # fails at LOAD time with a confusing partial-mmap error, so every
    # artifact is checked before the server execs.
    grep -q 'missing asset' "$SERVE"
    grep -q 'download-frank-primary.sh' "$SERVE"
}

@test "the prompt-cache cap is set below the RAM the host can spare" {
    grep -q '^CACHE_RAM=16384$' "$ENV_FILE"
    grep -q -- '--cache-ram "$CACHE_RAM"' "$SERVE"
}

@test "the deployer retires the lucebox quadlet, gates every part and waits out the port" {
    # The cutover order: the user-scope quadlet is stopped and its
    # generated .container moved to dated home trash BEFORE the root unit
    # binds 7770 (nothing starts until the port is released — the 2026-09-26
    # and 2026-09-16 cutover failures were both here).
    grep -q 'retire_lucebox_primary_quadlet' "$REMOTE_DEPLOY"
    grep -q 'systemctl --user stop frank-primary.service' "$REMOTE_DEPLOY"
    grep -q 'relink_unit frank-primary' "$REMOTE_DEPLOY"
    grep -q 'systemctl enable frank-primary.service' "$REMOTE_DEPLOY"
    grep -q 'systemctl restart frank-primary.service' "$REMOTE_DEPLOY"
    grep -q 'wait_port_free 7770' "$REMOTE_DEPLOY"
    grep -q '127.0.0.1:7770/health' "$REMOTE_DEPLOY"
}

@test "the deployer gates the six-part payload at declared byte counts" {
    # stat -c %s, never wc -c — wc read the whole 377 GiB lucebox file for
    # minutes on 2026-09-26 before it could reach the cutover. A partial
    # download must never be served.
    grep -q 'LLM_PRIMARY_PART_SIZES' "$REMOTE_DEPLOY"
    grep -q 'stat -c %s' "$REMOTE_DEPLOY"
    grep -q '2786568256' "$REMOTE_DEPLOY"
    grep -q '907542944' "$REMOTE_DEPLOY"
    grep -q 'wait_for_health frank-primary http://127.0.0.1:7770/health 1800' "$REMOTE_DEPLOY"
}