#!/usr/bin/env bats
# Seam: frank-primary — the Dankserver LLM endpoint on :7770.
#
# This file asserts the LUCEBOX shape (the 2026-09-26 cutover that replaced
# frank-medium): a rootless Quadlet running the lucebox DS4.1 engine on the
# two R9700s, with the model mmapped out of /home/dank/models and the
# entrypoint/healthcheck mounted straight out of this checkout.

load helpers

UNIT="$REPO_ROOT/dankserver/frank-primary/quadlet/frank-primary.container"
EP="$REPO_ROOT/dankserver/frank-primary/frank-primary-entrypoint.sh"
HC="$REPO_ROOT/dankserver/frank-primary/frank-primary-healthcheck.py"

@test "the frank-primary quadlet file and its mounted scripts exist" {
    [ -f "$UNIT" ]
    [ -x "$EP" ]
    [ -f "$HC" ]
    # The healthcheck is python; a syntax error would leave the container
    # permanently unhealthy with the failure hidden inside HealthCmd.
    python3 -m py_compile "$HC"
}

@test "frank-primary is boot-persistent and self-healing" {
    # Rootless Podman does not auto-start bare containers and restart:
    # unless-stopped does not survive shutdown's explicit stop. The unit must
    # carry both the boot symlink and a restart policy (2026-08-26 incident:
    # a compose-only Caddy never came back after a reboot).
    grep -q '^WantedBy=default.target' "$UNIT"
    grep -qE '^Restart=(always|on-failure)' "$UNIT"
}

@test "frank-primary binds the host network and needs no published port" {
    # luce_server binds 0.0.0.0:7770 directly, so the container takes the
    # host netns. A PublishPort would be dead config.
    grep -q -- '--network=host' "$UNIT"
    ! grep -q '^PublishPort=' "$UNIT"
}

@test "frank-primary reaches both R9700s and hides the Raphael iGPU" {
    # /dev/kfd + /dev/dri via AddDevice; HIP_VISIBLE_DEVICES=0,1 keeps the
    # host's Raphael iGPU (index 2) out of the enumeration so the engine's
    # device picks cannot land on it.
    grep -q '^AddDevice=/dev/kfd' "$UNIT"
    grep -q '^AddDevice=/dev/dri' "$UNIT"
    grep -q '^Environment=HIP_VISIBLE_DEVICES=0,1$' "$UNIT"
}

@test "frank-primary never names a bare HIP-reserved env var" {
    # The HIP runtime reads bare TEMP for its JIT cache path (the 2026-08-13
    # incident: TEMP=1.0 sent the JIT cache to path "1.0" and segfaulted every
    # load). HOST and GPU_MAX_HEAP_SIZE are the same class. The unit's
    # Environment= lines must not define them; the entrypoint exports
    # GPU_MAX_HW_QUEUES (explicitly not GPU_MAX_HEAP_SIZE).
    ! grep -qE '^Environment=(TEMP|HOST|GPU_MAX_HEAP_SIZE)=' "$UNIT"
    ! grep -qE '^(export )?(TEMP|HOST|GPU_MAX_HEAP_SIZE)=' "$EP"
}

@test "the unit mounts the entrypoint and healthcheck from the checkout" {
    # deploy.sh git-pulls this checkout before dispatching, so a Volume
    # reference is how an edit here reaches the container without an image
    # rebuild. Absolute host paths, read-only.
    grep -q 'Volume=/home/dank/serverAppConfigs/dankserver/frank-primary/frank-primary-entrypoint.sh:/usr/local/bin/frank-primary-entrypoint.sh:ro' "$UNIT"
    grep -q 'Volume=/home/dank/serverAppConfigs/dankserver/frank-primary/frank-primary-healthcheck.py:/usr/local/bin/frank-primary-healthcheck.py:ro' "$UNIT"
}

@test "first-start patience is configured on both sides of the health check" {
    # Cold start page-ins the dense weights and builds the graphs; the
    # container must not be killed as unhealthy while that happens, and the
    # deployer must wait the same order of magnitude.
    grep -q '^HealthStartPeriod=1800s' "$UNIT"
    grep -q '^TimeoutStartSec=1800$' "$UNIT"
    grep -q 'wait_container_healthy frank-primary 1800' \
        "$REPO_ROOT/scripts/deploy-remote.sh"
}

@test "the deployer refuses to start without image and complete payload" {
    # A 377 GiB partial download must never be served: the handler gates on
    # the image being present and the model file existing at its exact
    # declared byte count (stat -c %s, never wc -c — wc read the whole stream
    # for minutes on 2026-09-26).
    grep -q 'deploy_llm_primary() {' "$REPO_ROOT/scripts/deploy-remote.sh"
    grep -q 'podman image exists localhost/lucebox-rocm:gfx1201' \
        "$REPO_ROOT/scripts/deploy-remote.sh"
    grep -q 'want_size=405349859328' "$REPO_ROOT/scripts/deploy-remote.sh"
    grep -q 'stat -c %s' "$REPO_ROOT/scripts/deploy-remote.sh"
}

@test "the deployer gates on the port actually being free" {
    # 7770 is a host-network bind: the previous holder must release it before
    # the new container can be created, or pasta's bind fails at create time
    # and the failure hides behind Restart=.
    grep -q 'wait_port_free 7770' "$REPO_ROOT/scripts/deploy-remote.sh"
}