gamedev-the-steward/tests/simulation_scaling_benchmark_test.gd

extends SceneTree

const SimulationManagerScript := preload("res://simulation/SimulationManager.gd")
const BenchmarkScript := preload("res://simulation/benchmark/SimulationScalingBenchmark.gd")


class CoverageDroppingManager:
	extends "res://simulation/SimulationManager.gd"

	var drop_after_simulation_ticks := -1
	var simulation_ticks_seen := 0
	var removed_combatant_id: StringName = &""

	func simulate_tick() -> void:
		super()
		simulation_ticks_seen += 1
		if simulation_ticks_seen != drop_after_simulation_ticks or npcs.is_empty():
			return
		removed_combatant_id = SimulationIds.npc_combatant_id(npcs[-1].id)
		conflict_system.combatants.erase(removed_combatant_id)


var failures: Array[String] = []


func _initialize() -> void:
	call_deferred("_run")


func _run() -> void:
	var first := _run_case(9001)
	var repeated := _run_case(9001)
	var different_seed := _run_case(9002)
	_check(not first.is_empty(), "The benchmark fixture should produce one result")
	if first.is_empty():
		_finish()
		return
	_check(first["fixture_valid"], "The prepared benchmark state should pass schema validation")
	_check(
		(
			int(first["schema_version"]) == 2
			and SimulationScalingBenchmark.SCHEMA_VERSION == 2
			and (
				int(first["simulation_state_schema_version"])
				== SimulationStateRecord.SCHEMA_VERSION
			)
			and StringName(first["workload_id"]) == &"full_fidelity_combatant_headless_arrival_v2"
			and (
				SimulationScalingBenchmark.WORKLOAD_ID
				== &"full_fidelity_combatant_headless_arrival_v2"
			)
			and int(first["population"]) == 12
			and int(first["npc_combatant_count"]) == 12
			and bool(first["npc_combatant_coverage_valid"])
			and int(first["fixture_npc_combatant_count"]) == 12
			and bool(first["fixture_combatants_valid"])
			and int(first["history_seed_events"]) == 24
			and int(first["measured_ticks"]) == 8
			and int(first["npc_updates"]) == 96
			and is_equal_approx(float(first["tick_interval"]), 1.2)
			and int(first["end_tick"]) - int(first["start_tick"]) == 8
		),
		"The result should identify the exact workload and measured update count"
	)
	_check(
		(
			int(first["elapsed_usec"]) > 0
			and int(first["simulation_usec"]) > 0
			and int(first["arrival_usec"]) > 0
			and int(first["start_state_bytes"]) > 0
			and int(first["end_state_bytes"]) >= int(first["start_state_bytes"])
			and int(first["arrivals_processed"]) > 0
			and int(first["events_recorded"]) > 0
			and int(first["end_event_count"]) >= 24
			and String(first["final_checksum"]).length() == 64
		),
		"The benchmark should report timing, state growth, updates, history, and a checksum"
	)
	for deterministic_key in [
		"final_checksum",
		"start_state_bytes",
		"end_state_bytes",
		"state_growth_bytes",
		"start_event_count",
		"end_event_count",
		"events_recorded",
		"start_known_reference_count",
		"end_known_reference_count",
		"arrivals_processed",
		"warmup_arrivals",
		"tick_interval",
		"npc_combatant_count",
		"npc_combatant_coverage_valid",
	]:
		_check(
			first[deterministic_key] == repeated[deterministic_key],
			"Repeated benchmark runs should preserve %s" % deterministic_key
		)
	_check(
		first["final_checksum"] != different_seed["final_checksum"],
		"A different fixture seed should produce a different deterministic checksum"
	)
	_check(
		_coverage_loss_is_rejected(2, 3, 2),
		"Coverage lost on the final warmup tick should reject the benchmark result"
	)
	_check(
		_coverage_loss_is_rejected(2, 3, 5),
		"Coverage lost on the final measured tick should reject the benchmark result"
	)
	_finish()


func _run_case(seed_value: int) -> Dictionary:
	var manager := SimulationManagerScript.new()
	manager.simulation_seed = seed_value
	manager.debug_logs = false
	manager.set_process(false)
	root.add_child(manager)
	var benchmark := BenchmarkScript.new()
	if not benchmark.prepare_manager(manager, 12, 24, seed_value):
		manager.free()
		return {}
	var fixture_valid := SimulationStateRecord.from_json(manager.serialize_state()) != null
	var fixture_npc_combatant_count := 0
	var fixture_combatants_valid := true
	for npc in manager.npcs:
		var combatant: CombatantStateRecord = manager.conflict_system.get_combatant(
			SimulationIds.npc_combatant_id(npc.id)
		)
		if (
			combatant == null
			or combatant.get_npc_id() != npc.id
			or combatant.get_display_name() != npc.npc_name
			or not combatant.get_position().is_equal_approx(npc.position)
		):
			fixture_combatants_valid = false
		else:
			fixture_npc_combatant_count += 1
	var result: Dictionary = benchmark.measure_manager(manager, 12, 24, 2, 8)
	result["fixture_valid"] = fixture_valid
	result["fixture_npc_combatant_count"] = fixture_npc_combatant_count
	result["fixture_combatants_valid"] = fixture_combatants_valid
	manager.free()
	return result


func _coverage_loss_is_rejected(
	warmup_ticks: int, measured_ticks: int, drop_after_simulation_ticks: int
) -> bool:
	var manager := CoverageDroppingManager.new()
	manager.simulation_seed = 9010
	manager.debug_logs = false
	manager.set_process(false)
	root.add_child(manager)
	var benchmark := BenchmarkScript.new()
	var prepared := benchmark.prepare_manager(manager, 4, 0, manager.simulation_seed)
	if not prepared:
		manager.free()
		return false
	var target_id := SimulationIds.npc_combatant_id(manager.npcs[-1].id)
	var target_existed := manager.conflict_system.get_combatant(target_id) != null
	manager.drop_after_simulation_ticks = drop_after_simulation_ticks
	var result: Dictionary = benchmark.measure_manager(manager, 4, 0, warmup_ticks, measured_ticks)
	var rejected_after_exact_drop := (
		target_existed
		and manager.simulation_ticks_seen == drop_after_simulation_ticks
		and manager.removed_combatant_id == target_id
		and manager.conflict_system.get_combatant(target_id) == null
		and result.is_empty()
	)
	manager.free()
	return rejected_after_exact_drop


func _check(condition: bool, message: String) -> void:
	if not condition:
		failures.append(message)


func _finish() -> void:
	if failures.is_empty():
		print("[TEST] Simulation scaling benchmark passed: valid fixture -> stable metrics")
		quit(0)
		return
	for failure in failures:
		push_error("[TEST] " + failure)
	quit(1)