serverAppConfigs/tests/llm_deploy_gates.bats

#!/usr/bin/env bats
# Seam: the deployer's LLM handlers are the twin of the serve scripts'
# artifact gates (the 2026-10-01 crash-loop: a green deploy against a
# missing payload left a restart-looping unit and a dark endpoint).
#
# These tests EXECUTE scripts/deploy-remote.sh's LLM handlers in a sandbox
# (tests/deploy_sandbox.bash): every host touchpoint is a stub, the artifacts
# are fixtures, and the assertions are exit status, the refusal on stderr,
# and what the handler asked systemd to do. A handler that started the unit
# before checking its artifacts would pass a text-grep seam and fail here.

load helpers
load deploy_sandbox

setup() { sandbox_setup; }
teardown() { sandbox_teardown; }

@test "the dragoon handler refuses when the engine image is not in storage" {
    export STUB_IMAGE=
    run_handler dankclaw frank-dragoon
    [ "$status" -ne 0 ]
    [[ "$output" == *"frank-dragoon: image:"*"not in podman storage"* ]]
    [ "$(restarts_requested)" = "0" ]
}

@test "the dragoon handler refuses a truncated checkpoint, pointing at the fetch" {
    truncate -s 9 "$STAGE/models/ck.hgn"
    run_handler dankclaw frank-dragoon
    [ "$status" -ne 0 ]
    [[ "$output" == *"checkpoint: is 9 bytes, expected 10"* ]]
    # The refusal is only useful if it names the remedy: the fetch script
    # re-verifies byte counts and hashes.
    [[ "$output" == *"download-frank-dragoon-flashnext.sh"* ]]
    [ "$(restarts_requested)" = "0" ]
}

@test "the dragoon handler refuses a symlinked tokenizer file" {
    # The flat-tokenizer law: a HuggingFace cache snapshot links its
    # members, and the link dangles inside the container mount.
    rm "$STAGE/models/tokenizer/vocab.json"
    ln -s /nowhere/vocab.json "$STAGE/models/tokenizer/vocab.json"
    run_handler dankclaw frank-dragoon
    [ "$status" -ne 0 ]
    [[ "$output" == *"frank-dragoon: tokenizer: $STAGE/models/tokenizer/vocab.json is missing or a symlink"* ]]
    [ "$(restarts_requested)" = "0" ]
}

@test "the dragoon handler starts the unit once every artifact gate passes" {
    run_handler dankclaw frank-dragoon
    [ "$status" -eq 0 ]
    grep -q 'restart frank-dragoon.service' "$STAGE/systemctl.log"
    grep -qx 'rm -f frank-dragoon frank-dragoon-halogen' "$STAGE/podman.log"
}

@test "the zealot handler refuses when the llama.cpp runtime is not executable" {
    # The runtime is an operator-built binary; a tree that compiled but lost
    # its exec bit must refuse exactly like a missing one.
    rm "$STAGE/models/llama-server"
    run_handler dankclaw frank-zealot
    [ "$status" -ne 0 ]
    [[ "$output" == *"frank-zealot: runtime: missing at $STAGE/models/llama-server"* ]]
    [[ "$output" == *"cmake"* ]]
    [ "$(restarts_requested)" = "0" ]
}

@test "the zealot handler refuses a missing projector — a text-only endpoint is not deployable" {
    # The projector IS the vision capability: deploying without it silently
    # ships a text-only endpoint.
    rm "$STAGE/models/mmproj.gguf"
    run_handler dankclaw frank-zealot
    [ "$status" -ne 0 ]
    [[ "$output" == *"frank-zealot: mmproj: missing at $STAGE/models/mmproj.gguf"* ]]
    [ "$(restarts_requested)" = "0" ]
}

@test "the zealot handler starts the unit once every artifact gate passes" {
    run_handler dankclaw frank-zealot
    [ "$status" -eq 0 ]
    grep -q 'restart frank-zealot.service' "$STAGE/systemctl.log"
}

@test "the archon handler refuses when the radiance image is not in storage" {
    export STUB_IMAGE=
    run_handler dankserver frank-archon
    [ "$status" -ne 0 ]
    [[ "$output" == *"frank-archon: image:"*"not in podman storage"* ]]
    [[ "$output" == *"podman pull"* ]]
    [ "$(restarts_requested)" = "0" ]
}

@test "the archon handler refuses a .rad below the env's size floor" {
    truncate -s 1048576 "$STAGE/models/payload.rad"   # 1 MiB, far under the floor
    archon_payload_env
    export STUB_IMAGE="$ARCHON_IMAGE"
    run_handler dankserver frank-archon
    [ "$status" -ne 0 ]
    [[ "$output" == *"frank-archon: .rad: is 1 MiB, expected >= "* ]]
    [[ "$output" == *"convert-swift15-w4dn8.sh"* ]]
    [ "$(restarts_requested)" = "0" ]
}

@test "the archon handler clears the legacy container identities and relinks the unit" {
    # The retired identities (the R9V container, the ad hoc probe, the glm
    # experiment) hold the same GPUs, so a deploy that leaves one running
    # leaves the new engine unable to bind. The unit link is the root-unit
    # shape's whole install.
    archon_payload_env 2
    export STUB_IMAGE="$ARCHON_IMAGE"
    run_handler dankserver frank-archon
    [ "$status" -eq 0 ]
    grep -q 'restart frank-archon.service' "$STAGE/systemctl.log"
    [ -L "$STAGE/systemd/frank-archon.service" ]
    local ctr
    for ctr in frank-archon frank-archon-qwen frank-archon-r9v qwen-fp8 glm-probe; do
        grep -qx "rm -f $ctr" "$STAGE/podman.log"
    done
}

@test "no LLM handler reports green when its unit has no MainPID behind the port" {
    # The 2026-09-26 false green: a leftover probe held :7770 and satisfied
    # the health curl while the real unit was stopped.
    archon_payload_env 2
    export STUB_IMAGE="$ARCHON_IMAGE"
    export STUB_MAIN_PID=0
    run_handler dankserver frank-archon
    [ "$status" -ne 0 ]
    [[ "$output" == *"frank-archon.service has no MainPID"* ]]
}

@test "a refused LLM handler leaves its service pending in the deploy state" {
    export STUB_IMAGE=
    run_handler dankserver frank-archon
    [ "$status" -ne 0 ]
    grep -q 'status=pending' "$STAGE/state/frank-archon"
    [ ! -e "$STAGE/state/frank-zealot" ]
}