#!/usr/bin/env bats
# Tests for scripts/benchmark/compare.sh — result comparison logic

load test_helper.sh

setup() {
    source_lib common.sh
    source_lib format.sh
    BEFORE_DIR="$(mktemp -d)"
    AFTER_DIR="$(mktemp -d)"
}

teardown() {
    rm -rf "$BEFORE_DIR" "$AFTER_DIR"
}

write_summary() {
    local dir="$1" json="$2"
    echo "$json" > "$dir/summary.json"
}

write_system_state() {
    local dir="$1" json="$2"
    echo "$json" > "$dir/system-state.json"
}

# ── Basic comparison ─────────────────────────────────────

@test "compare: shows improvement when after > before" {
    write_summary "$BEFORE_DIR" '{"results":[{"model":"qwen3","backend":"Vulkan","test":"pp512","tokens_per_sec":500.0,"file":"test.log","size":"4GB","raw":"500.0"}]}'
    write_summary "$AFTER_DIR" '{"results":[{"model":"qwen3","backend":"Vulkan","test":"pp512","tokens_per_sec":600.0,"file":"test.log","size":"4GB","raw":"600.0"}]}'
    write_system_state "$BEFORE_DIR" '{"memory":{"vram_total_bytes":0},"kernel":{},"tuned_profile":"throughput-performance"}'
    write_system_state "$AFTER_DIR" '{"memory":{"vram_total_bytes":0},"kernel":{},"tuned_profile":"throughput-performance"}'

    run bash "$PROJECT_ROOT/scripts/benchmark/compare.sh" "$BEFORE_DIR" "$AFTER_DIR"
    assert_success
    assert_output --partial "500.0"
    assert_output --partial "600.0"
}

@test "compare: shows regression when after < before" {
    write_summary "$BEFORE_DIR" '{"results":[{"model":"qwen3","backend":"Vulkan","test":"tg128","tokens_per_sec":15.0,"file":"test.log","size":"4GB","raw":"15.0"}]}'
    write_summary "$AFTER_DIR" '{"results":[{"model":"qwen3","backend":"Vulkan","test":"tg128","tokens_per_sec":12.0,"file":"test.log","size":"4GB","raw":"12.0"}]}'
    write_system_state "$BEFORE_DIR" '{"memory":{},"kernel":{},"tuned_profile":""}'
    write_system_state "$AFTER_DIR" '{"memory":{},"kernel":{},"tuned_profile":""}'

    run bash "$PROJECT_ROOT/scripts/benchmark/compare.sh" "$BEFORE_DIR" "$AFTER_DIR"
    assert_success
    assert_output --partial "12.0"
}

@test "compare: handles empty results gracefully" {
    write_summary "$BEFORE_DIR" '{"results":[]}'
    write_summary "$AFTER_DIR" '{"results":[]}'
    write_system_state "$BEFORE_DIR" '{"memory":{},"kernel":{},"tuned_profile":""}'
    write_system_state "$AFTER_DIR" '{"memory":{},"kernel":{},"tuned_profile":""}'

    run bash "$PROJECT_ROOT/scripts/benchmark/compare.sh" "$BEFORE_DIR" "$AFTER_DIR"
    assert_success
    assert_output --partial "No comparable results"
}

@test "compare: fails without summary.json" {
    run bash "$PROJECT_ROOT/scripts/benchmark/compare.sh" "$BEFORE_DIR" "$AFTER_DIR"
    assert_failure
    assert_output --partial "No summary.json"
}

@test "compare: shows usage when called without args" {
    run bash "$PROJECT_ROOT/scripts/benchmark/compare.sh"
    assert_failure
    assert_output --partial "Usage"
}

@test "compare: detects config changes between runs" {
    write_summary "$BEFORE_DIR" '{"results":[{"model":"m","backend":"b","test":"t","tokens_per_sec":1.0,"file":"f","size":"s","raw":"1.0"}]}'
    write_summary "$AFTER_DIR" '{"results":[{"model":"m","backend":"b","test":"t","tokens_per_sec":2.0,"file":"f","size":"s","raw":"2.0"}]}'
    write_system_state "$BEFORE_DIR" '{"memory":{"vram_total_bytes":34359738368},"kernel":{"param_iommu":"","param_gttsize":"","param_pages_limit":""},"tuned_profile":"throughput-performance"}'
    write_system_state "$AFTER_DIR" '{"memory":{"vram_total_bytes":536870912},"kernel":{"param_iommu":"pt","param_gttsize":"61440","param_pages_limit":"15728640"},"tuned_profile":"accelerator-performance"}'

    run bash "$PROJECT_ROOT/scripts/benchmark/compare.sh" "$BEFORE_DIR" "$AFTER_DIR"
    assert_success
    assert_output --partial "Configuration changes"
}