#!/usr/bin/env bats
# Seam: ComfyUI ROCm GPU configuration on Dankclaw.
# The gfx1151-enabled PyTorch build is the only verified GPU path on Strix
# Halo. The compose must:
#   - build from a Containerfile based on the gfx1151 ROCm torch image
#   - pass /dev/kfd and /dev/dri to the container
#   - NOT pass --cpu
#   - grant GPU access via world-writable compute nodes (udev MODE 0666), not
#     named-group membership, because systemd user-unit spawns carry NO
#     supplementary groups at spawn time
#
# STATUS (2026-09-16): ComfyUI is a Quadlet unit, not a compose service. The
# build still comes from Containerfile.comfyui (AMD's gfx1151 torch base) via
# the deployer's build_compose_image, and the wiring now lives in
# dankclaw/comfyui/quadlet/comfyui.container: /dev/kfd + /dev/dri, keep-groups
# only, and the udev rule at dankclaw/udev/99-comfyui-gpu-access.rules (MODE
# 0666 on kfd + renderD*) for compute-node access, because systemd user-unit
# spawns carry no supplementary groups. The move happened after the compose
# container went stale — created before the GPU declarations existed, then
# restarted 9,146 times without them. See
# serverAppConfigs-docs/Research/ComfyUI ROCm and Vulkan.md.

load helpers

@test "comfyui builds from the gfx1151 ROCm Containerfile" {
    # The image is built by the deployer (build_compose_image comfyui, which
    # resolves dankclaw/Containerfile.comfyui) and referenced by the unit.
    grep -q "comfyui)" "$REPO_ROOT/scripts/deploy-remote.sh"
    grep -q 'image=comfyui-rocm:gfx1151' "$REPO_ROOT/scripts/deploy-remote.sh"
    grep -q 'containerfile=dankclaw/Containerfile.comfyui' "$REPO_ROOT/scripts/deploy-remote.sh"
    local unit="$REPO_ROOT/dankclaw/comfyui/quadlet/comfyui.container"
    grep -q '^Image=localhost/comfyui-rocm:gfx1151$' "$unit" \
        || { echo "unit must run the locally built image"; return 1; }
    # One owner per container name: a surviving compose service would fight the
    # unit for the container, which is how the stale one stayed alive. The file
    # itself is retired (observability_quadlet.bats asserts that), so here the
    # regression to catch is a re-added entry — the check must not go hollow
    # just because the file is absent.
    local cf="$REPO_ROOT/dankclaw/compose.yaml"
    [ ! -f "$cf" ] || ! grep -qE '^\s+comfyui:' "$cf"
}

@test "comfyui Containerfile is based on the gfx1151 torch image" {
    # Resolve the Containerfile from the deployer's declaration — the file the
    # build actually uses — not from the filesystem. A `find … | head -1` here
    # once returned whichever Containerfile the directory listing happened to
    # put first (dankclaw/alloy/Containerfile), so the test failed for sessions
    # while the real ComfyUI Containerfile was correct, and it would equally
    # have passed on a wrong file. Compose no longer names it: ComfyUI is a
    # Quadlet unit and the image is built by deploy_comfyui.
    local cf="$REPO_ROOT/dankclaw/Containerfile.comfyui"
    grep -q 'containerfile=dankclaw/Containerfile.comfyui' "$REPO_ROOT/scripts/deploy-remote.sh" \
        || { echo "deployer no longer builds that Containerfile"; return 1; }
    [ -f "$cf" ] || { echo "$cf does not exist"; return 1; }
    grep -q "gfx1151" "$cf" || { echo "$cf does not reference gfx1151"; return 1; }
    grep -q "FROM" "$cf" || { echo "$cf has no FROM"; return 1; }
}

@test "comfyui passes /dev/kfd and /dev/dri to the container" {
    # Read the Quadlet unit, not compose: ComfyUI left compose on 2026-09-16
    # after a stale, device-less container was restarted 9,146 times by
    # `restart: unless-stopped` (see comfyui/quadlet/comfyui.container).
    local unit="$REPO_ROOT/dankclaw/comfyui/quadlet/comfyui.container"
    [ -f "$unit" ]
    grep -q '^AddDevice=/dev/kfd$' "$unit" || { echo "no /dev/kfd"; return 1; }
    grep -q '^AddDevice=/dev/dri$' "$unit" || { echo "no /dev/dri"; return 1; }
}

@test "comfyui does not run with --cpu" {
    local unit="$REPO_ROOT/dankclaw/comfyui/quadlet/comfyui.container"
    local wrapper="$REPO_ROOT/dankclaw/comfyui-start.sh"
    local exec_line
    exec_line=$(grep -E '^Exec=' "$unit")
    # The exec line points at the startup wrapper; the actual flags live there.
    local target
    case "$exec_line" in
        *comfyui-start.sh*) target="$wrapper" ;;
        *) target="$unit" ;;
    esac
    case "$(grep -E 'main\.py|--cpu' "$target")" in
        *--cpu*) echo "comfyui must not pass --cpu (ROCm GPU build)"; return 1 ;;
    esac
    case "$(grep -E 'main\.py|--listen' "$target")" in
        *--listen*) ;;
        *) echo "comfyui must listen on 0.0.0.0"; return 1 ;;
    esac
}

@test "comfyui GPU access uses keep-groups + udev MODE 0666, not named groups" {
    python3 - "$REPO_ROOT/dankclaw/comfyui/quadlet/comfyui.container" "$REPO_ROOT/dankclaw/udev/99-comfyui-gpu-access.rules" <<'PYEOF'
import sys, re
unit = open(sys.argv[1]).read()
groups = re.findall(r"^GroupAdd=(.*)$", unit, re.M)
# User-unit spawns carry NO supplementary groups, so named group_add entries
# (video, render) can never be honored at spawn time. The deployed contract is
# keep-groups plus world-writable compute nodes via the udev rule; a future
# edit that drops either half must fail here.
assert groups == ["keep-groups"], \
    f"comfyui GroupAdd must be exactly ['keep-groups']; got: {groups}"
rule = open(sys.argv[2]).read()
assert 'KERNEL=="kfd", MODE="0666"' in rule, \
    "udev rule must grant MODE 0666 on kfd with NO SUBSYSTEM guard (misc-class devices have no subsystem to match)"
assert 'KERNEL=="renderD*", SUBSYSTEM=="drm", MODE="0666"' in rule, \
    "udev rule must grant MODE 0666 on renderD* (SUBSYSTEM drm guard)"
print("GPU access contract OK")
PYEOF
}