CosmicClash/Game/scripts/network_manager.gd

extends Node

# Autoload (project.godot [autoload] NetworkManager). Owns transport-neutral
# hosting, joining, shutdown, and connection-state signals. Lives
# at a fixed autoload path so RPC NodePaths never depend on which scene is
# loaded (§1.3 of multiplayer-todo.md's derived decisions).
#
# server_relay = false is set the moment a peer exists: the default `true`
# lets any client rpc() any other client *through the server*, which this
# project's server-authoritative model must never allow — §2.1 calls this
# out as the single highest-value one-line security change in the document.
#
# IMPORTANT, learned the hard way (tests/net_smoke.gd): don't call
# shutdown()/close the peer the instant connected_to_server or peer_connected
# fires. ENet's connect handshake isn't fully settled on the *other* side the
# moment your own side's signal fires — the final ACK still needs a couple
# more poll() cycles to actually reach the wire. Closing immediately drops
# it and leaves the other side's handshake permanently incomplete (it will
# never see peer_connected/connected_to_server at all). Callers that shut
# down right after a fresh connection should let a frame or two pass first.
#
# Manual polling (task 1.3): SceneTree's automatic multiplayer poll runs on
# the *idle* frame, so an rpc() issued from _physics_process waits up to a
# full frame before it's actually pushed onto the wire — and the return leg
# pays the same tax again. set_multiplayer_poll_enabled(false) below turns
# that off; every caller that sends or expects to receive on a tight cadence
# must now call NetworkManager.poll() itself. The intended placement per
# multiplayer-todo.md §7 task 1.3 (client: end of _physics_process after
# sending input, plus top of both _process and _physics_process for receive;
# server: tick start to drain, tick end to flush) has no real per-tick caller
# yet — that lands with the input/snapshot pipeline (tasks 1.4+, Phase 2-3).
# Until then, anything driving a connection (tests/net_smoke.gd included)
# must poll() every frame itself or nothing will ever be sent or received.

signal client_connected(peer_id: int)
signal client_disconnected(peer_id: int)
signal connected_to_server()
signal connection_failed()
signal disconnected_from_server()
signal clock_updated(rtt_ms: float, offset_ms: float)
# Fires at the top of every shutdown() call, whether this process was
# hosting, joined, or already offline, and regardless of *why* (deliberate
# Leave/Cancel, or an incoming disconnect from the other side). Adversarial
# review found MatchNet.roster had no path that cleared it when a HOST
# stopped hosting — connected_to_server/disconnected_from_server only cover
# the client side — so a host -> lobby -> leave -> host-again cycle left a
# permanent phantom player. Listeners that need per-role cleanup should
# still use the more specific signals above; this one exists so "something
# is about to reset the connection, drop anything you were keeping" has
# exactly one place to hook regardless of role.
signal shutting_down()

const DEFAULT_PORT := 7777
const MAX_CLIENTS := 32
const TRANSPORT_ENET := "enet"
const TRANSPORT_STEAM := "steam"

const EnetTransportScript = preload("res://scripts/enet_transport.gd")
const SteamTransportScript = preload("res://scripts/steam_transport.gd")

# Clock (task 1.8, §4.7): client pings the server once a second on the
# reliable control channel; clock_offset_ms is the min-RTT sample in a
# rolling window, because the lowest-RTT sample has the least queueing
# error. get_server_time_estimate_ms() is the thing every later phase
# (interpolation delay, tick_offset seeding) actually wants — everything
# else here exists to produce it.
const PING_INTERVAL_SEC := 1.0
const CLOCK_WINDOW_SEC := 5.0

var is_server := false
var is_client := false
var _peer: MultiplayerPeer   # keep a strong ref alongside multiplayer.multiplayer_peer
var active_transport := ""

var rtt_ms := -1.0            # min-RTT sample currently in the window; -1 = no sample yet
var clock_offset_ms := 0.0    # add to a local Time.get_ticks_msec() reading to estimate the server's clock
var _clock_samples: Array[Dictionary] = []
var _ping_accum_sec := 0.0

# Jitter (task 3.7's debug overlay): RFC3550-style EWMA of the deviation
# between consecutive RAW (not min-filtered) RTT samples — rtt_ms itself is
# a min-RTT, deliberately insensitive to jitter by design (§4.7), so a
# separate, unfiltered running estimate is needed to actually see it.
const JITTER_EWMA_ALPHA := 1.0 / 16.0   # matches RFC3550's own smoothing factor
var jitter_ms := 0.0
var _last_raw_rtt_ms := -1.0


func _ready() -> void:
	get_tree().set_multiplayer_poll_enabled(false)
	multiplayer.peer_connected.connect(_on_peer_connected)
	multiplayer.peer_disconnected.connect(_on_peer_disconnected)
	multiplayer.connected_to_server.connect(_on_connected_to_server)
	multiplayer.connection_failed.connect(_on_connection_failed)
	multiplayer.server_disconnected.connect(_on_server_disconnected)


func _process(delta: float) -> void:
	# is_client turns true the instant join() is called, before the ENet
	# handshake actually completes (or fails) — a slow or refused connect
	# attempt would otherwise leave this trying to rpc_id() on a peer
	# that's still CONNECTING (or already failed), which Godot logs as
	# "Trying to call an RPC via a multiplayer peer which is not
	# connected." every single frame. Require the real transport state.
	if not is_client or _peer == null or _peer.get_connection_status() != MultiplayerPeer.CONNECTION_CONNECTED:
		return
	_ping_accum_sec += delta
	if _ping_accum_sec >= PING_INTERVAL_SEC:
		_ping_accum_sec = 0.0
		# Capture the timestamp now, before NetSim (task 2.8) can add any
		# simulated delay — see net_sim.gd's header comment for why.
		var send_ms := Time.get_ticks_msec()
		NetSim.send(func() -> void: _ping.rpc_id(1, send_ms), 1)


# Estimate of what the server's Time.get_ticks_msec() reads right now.
# Meaningless before the first pong lands (clock_offset_ms is 0.0 until then
# — callers needing round-trip-confirmed freshness should check rtt_ms >= 0).
func get_server_time_estimate_ms() -> float:
	return float(Time.get_ticks_msec()) + clock_offset_ms


# The single entry point every per-tick caller uses instead of relying on
# SceneTree's (now disabled) automatic poll. Safe to call with no peer set —
# polling the default OfflineMultiplayerPeer is a no-op.
func poll() -> void:
	multiplayer.poll()


func available_transports() -> PackedStringArray:
	var transports := PackedStringArray([TRANSPORT_ENET])
	if SteamTransportScript.new().is_available():
		transports.append(TRANSPORT_STEAM)
	return transports


func host(port: int = DEFAULT_PORT, max_clients: int = MAX_CLIENTS, transport: String = TRANSPORT_ENET) -> Error:
	shutdown()
	var implementation := _make_transport(transport)
	if implementation == null:
		return ERR_INVALID_PARAMETER
	var result: Dictionary = implementation.create_server(port, max_clients)
	var err := int(result.error)
	if err != OK:
		push_error("NetworkManager.host(%s): create_server failed (%s): %s" % [transport, error_string(err), String(result.get("reason", ""))])
		return err
	_peer = result.peer as MultiplayerPeer
	multiplayer.multiplayer_peer = _peer
	multiplayer.server_relay = false
	active_transport = transport
	is_server = true
	is_client = false
	return OK


func join(address: String, port: int = DEFAULT_PORT, transport: String = TRANSPORT_ENET) -> Error:
	shutdown()
	var implementation := _make_transport(transport)
	if implementation == null:
		return ERR_INVALID_PARAMETER
	var result: Dictionary = implementation.create_client(address, port)
	var err := int(result.error)
	if err != OK:
		push_error("NetworkManager.join(%s): create_client failed (%s): %s" % [transport, error_string(err), String(result.get("reason", ""))])
		return err
	_peer = result.peer as MultiplayerPeer
	multiplayer.multiplayer_peer = _peer
	multiplayer.server_relay = false
	active_transport = transport
	is_server = false
	is_client = true
	return OK


func shutdown() -> void:
	shutting_down.emit()
	# MultiplayerAPI's default multiplayer_peer is an OfflineMultiplayerPeer
	# sentinel, never null — closing that sentinel is a no-op, but assigning
	# multiplayer_peer = null (rather than a fresh OfflineMultiplayerPeer)
	# leaves the API in a state distinct from its own default, which is a
	# known source of confusing follow-on bugs (godotengine/godot#81540).
	# Always reset to a real OfflineMultiplayerPeer, never raw null.
	var peer := multiplayer.multiplayer_peer
	if peer != null and not (peer is OfflineMultiplayerPeer):
		peer.close()
	multiplayer.multiplayer_peer = OfflineMultiplayerPeer.new()
	_peer = null
	active_transport = ""
	is_server = false
	is_client = false
	rtt_ms = -1.0
	clock_offset_ms = 0.0
	_clock_samples.clear()
	_ping_accum_sec = 0.0
	jitter_ms = 0.0
	_last_raw_rtt_ms = -1.0


func _make_transport(transport: String) -> NetTransport:
	match transport:
		TRANSPORT_ENET:
			return EnetTransportScript.new()
		TRANSPORT_STEAM:
			return SteamTransportScript.new()
		_:
			push_error("NetworkManager: unknown transport '%s'" % transport)
			return null


@rpc("any_peer", "call_remote", "reliable")
func _ping(client_send_ms: int) -> void:
	if not multiplayer.is_server():
		return
	# Same rule as the client's send above: read the server's clock now, at
	# true receipt time, before NetSim can delay the reply — otherwise the
	# server's own outbound leg would be silently absorbed out of both the
	# RTT sample and the offset estimate instead of adding to them.
	var server_now := Time.get_ticks_msec()
	var sender_id := multiplayer.get_remote_sender_id()
	# A single poll() call can process several queued RPCs from the same
	# peer in one batch — an earlier one in that same batch (e.g. task 3.4's
	# abuse-triggered match_sim.gd disconnect_peer() call, or the peer
	# disconnecting for any other reason mid-batch) can leave this ping's
	# sender no longer a valid peer by the time its own turn in the batch
	# comes up. Empirically confirmed reachable with disconnect_peer()'s
	# default arguments (a graceful, non-forced disconnect — match_sim.gd's
	# own disconnect call tried force=true as an alternative and reverted
	# it, since that left Godot's own peer-list bookkeeping inconsistent
	# and produced far MORE of this exact class of error, not fewer:
	# hundreds vs. one, verified). NetSim's inactive/passthrough path (the
	# common case — no CLI flags) dispatches immediately with no
	# validation of its own, so check here rather than relying on it.
	if sender_id not in multiplayer.get_peers():
		return
	NetSim.send(func() -> void: _pong.rpc_id(sender_id, client_send_ms, server_now), sender_id)


@rpc("authority", "call_remote", "reliable")
func _pong(client_send_ms: int, server_now_ms: int) -> void:
	var now_ms := Time.get_ticks_msec()
	var sample_rtt := float(now_ms - client_send_ms)
	var sample_offset := float(server_now_ms) + sample_rtt / 2.0 - float(now_ms)
	if _last_raw_rtt_ms >= 0.0:
		var deviation := absf(sample_rtt - _last_raw_rtt_ms)
		jitter_ms += (deviation - jitter_ms) * JITTER_EWMA_ALPHA
	_last_raw_rtt_ms = sample_rtt
	_clock_samples.append({"t": now_ms, "rtt": sample_rtt, "offset": sample_offset})

	var cutoff := now_ms - int(CLOCK_WINDOW_SEC * 1000.0)
	_clock_samples = _clock_samples.filter(func(s: Dictionary) -> bool: return s["t"] >= cutoff)

	var best: Dictionary = _clock_samples[0]
	for sample: Dictionary in _clock_samples:
		if sample["rtt"] < best["rtt"]:
			best = sample
	rtt_ms = best["rtt"]
	clock_offset_ms = best["offset"]
	clock_updated.emit(rtt_ms, clock_offset_ms)


func _on_peer_connected(peer_id: int) -> void:
	client_connected.emit(peer_id)


func _on_peer_disconnected(peer_id: int) -> void:
	client_disconnected.emit(peer_id)


func _on_connected_to_server() -> void:
	connected_to_server.emit()


func _on_connection_failed() -> void:
	is_client = false
	connection_failed.emit()


func _on_server_disconnected() -> void:
	is_server = false
	is_client = false
	disconnected_from_server.emit()