serverAppConfigs/tests/frank_large_unit.bats

#!/usr/bin/env bats
# Seam: the frank-large unsloth-llama.cpp root unit on dankclaw.
#
# The 2026-09-21 cutover moved this service from the CIRU v4.4.1 runtime
# (jcbtc/Qwen3.8-Flash-CIRU-STRIX-Orca) onto the unsloth llama.cpp prebuilt
# (b11030-mix-5ff778e, ROCm gfx1151) serving
# unsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ4_XS, still as a ROOT unit: a
# prebuilt tarball with its own bundled ROCm has no container image to
# install and no generated unit to dodge. This seam pins what a flag list
# cannot show: the operator's one-stream / 200k shape, the payload the
# serve script refuses to start without, the explicit -md MTP wiring
# (sidecar auto-discovery does not search the mtp/ subfolder), a deploy
# handler that gates on the port, and the fact that the sweep for a stray
# benchmark run cannot take frank-small down with it.

load helpers

ENV_FILE="$REPO_ROOT/scripts/frank-large.env"
UNIT="$REPO_ROOT/scripts/frank-large.service"
SERVE="$REPO_ROOT/scripts/serve-frank-large.sh"
FETCH="$REPO_ROOT/scripts/download-frank-large-unsloth.sh"
REMOTE_DEPLOY="$REPO_ROOT/scripts/deploy-remote.sh"

@test "the frank-large unit, env and serve files exist where the deployer installs them from" {
    [ -f "$ENV_FILE" ]
    [ -f "$UNIT" ]
    [ -x "$SERVE" ]
}

@test "frank-large is boot-persistent, self-healing and unprivileged" {
    grep -q '^WantedBy=multi-user.target$' "$UNIT"
    grep -q '^Restart=on-failure$' "$UNIT"
    grep -q '^RestartSec=' "$UNIT"
    grep -q '^User=dank$' "$UNIT"
    # The engine pins staging buffers; the memlock budget must be unbounded
    # or the load fails on the RLIMIT.
    grep -q '^LimitMEMLOCK=infinity$' "$UNIT"
    # The unit runs the repo's own serve script with the repo's env.
    grep -q 'ExecStart=/home/dank/serverAppConfigs/scripts/serve-frank-large.sh' "$UNIT"
    grep -q 'FRANK_LARGE_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-large.env' "$UNIT"
}

@test "the operator's shape is one stream of 200k context with MTP on" {
    local ctx slots
    ctx="$(sed -nE 's/^CONTEXT_SIZE=([0-9]+)$/\1/p' "$ENV_FILE")"
    slots="$(sed -nE 's/^PARALLEL_SLOTS=([0-9]+)$/\1/p' "$ENV_FILE")"
    # 200000 is the operator's requested serving shape (2026-09-21); the
    # model's trained window is 262144.
    [ "$ctx" -eq 200000 ]
    # One stream.
    [ "$slots" -eq 1 ]
    grep -q '^ENABLE_MTP=1$' "$ENV_FILE"
}

@test "frank-large stays text-only until the projector is enabled" {
    grep -q '^ENABLE_VISION=0$' "$ENV_FILE"
    # The fleet's image path is frank-small; the projector is on disk and is
    # one env flip away, but models.yml declares frank-large text-only.
    grep -q -- '--mmproj' "$REPO_ROOT/scripts/serve-frank-small.sh"
}

@test "the serve script pins the prebuilt runtime and refuses a missing build" {
    grep -q 'unsloth-llama-b11030' "$SERVE"
    grep -q 'llama-server' "$SERVE"
    # A missing runtime or payload is a deploy error with a pointer, not a
    # restart loop.
    grep -q 'missing runtime' "$SERVE"
    grep -q 'missing target model' "$SERVE"
    grep -q 'missing MTP head' "$SERVE"
    # The Qwen3.8 template keeps prior thinking blocks across turns only
    # when the kwarg is set.
    grep -q 'preserve_thinking' "$SERVE"
}

@test "the serve script wires the MTP head explicitly and speculates" {
    # Sidecar auto-discovery does not search the mtp/ subfolder, so the head
    # must be passed with -md or the server runs at the main model's speed
    # with no error saying why.
    grep -q -- '-md "$MTP_FILE"' "$SERVE"
    grep -q -- '--spec-type draft-mtp' "$SERVE"
    grep -q 'mtp-Qwen3.8-Flash-Next-shared-Q8_0.gguf' "$SERVE"
}

@test "the payload is fetched resumably and verified against the live Hub tree" {
    grep -q 'unsloth/Qwen3.8-Flash-Next-GGUF' "$FETCH"
    grep -q -- '-fL -C -' "$FETCH"
    # The LFS oids come from the Hub tree API at verify time, not from a
    # file that could drift; each part's local sha256 is compared to its
    # oid and a mismatch fails the run.
    grep -q 'tree/main' "$FETCH"
    grep -q 'SHA256 MISMATCH' "$FETCH"
}

@test "the fleet endpoint and alias survive the cutover" {
    grep -q '^HOST=0.0.0.0$' "$ENV_FILE"
    grep -q '^PORT=7770$' "$ENV_FILE"
    grep -q '^MODEL_DIR=/home/dank/models/Qwen3.8-Flash-Next-UD-IQ4_XS$' "$ENV_FILE"
}

@test "the deploy handler retires the halogen quadlet without deleting it" {
    grep -q 'retire_halogen_large_quadlet' "$REMOTE_DEPLOY"
    grep -q 'HOME/.AGENTTRASH' "$REMOTE_DEPLOY"
    ! grep -qE '(^|[^[:alnum:]_])rm (-[a-zA-Z]+ )?.*frank-large' "$REMOTE_DEPLOY"
}

@test "the deploy handler installs the root unit, gates the port and refuses a missing payload" {
    grep -q 'relink_unit frank-large' "$REMOTE_DEPLOY"
    grep -q 'systemctl enable frank-large.service' "$REMOTE_DEPLOY"
    grep -q 'wait_port_free 7770' "$REMOTE_DEPLOY"
    grep -q '127.0.0.1:7770/health' "$REMOTE_DEPLOY"
    grep -q 'LLM_LARGE_MODEL' "$REMOTE_DEPLOY"
    grep -q 'LLM_LARGE_DRAFT' "$REMOTE_DEPLOY"
}

@test "the stray-run sweep cannot take frank-small down" {
    # frank-small on this host is ALSO a llama-server. The sweep must match
    # the model path, not the binary name, or a frank-large deploy restarts
    # the 3090 endpoint.
    grep -q "pkill -f 'Qwen3.8-Flash-Next-UD-IQ4_XS'" "$REMOTE_DEPLOY"
    # ...and only inside the large handler: extract it and check there is no
    # bare binary-name pkill in it.
    local large
    large="$(sed -n '/^deploy_llm_large() {/,/^}/p' "$REMOTE_DEPLOY")"
    ! grep -q 'pkill -x llama-server' <<<"$large"
}

@test "the halogen quadlet is archived, not live" {
    [ ! -e "$REPO_ROOT/dankclaw/frank-large/quadlet/frank-large.container" ]
    [ -f "$REPO_ROOT/dankclaw/.AGENTTRASH/frank-large.container.halogen" ]
}