CosmicClash/Game/scripts/match_sim.gd

extends Node

# Autoload (project.godot [autoload] MatchSim). Phase 2 simulation RPCs:
# match_config (server assigns arena + deterministic slot order from
# MatchNet.roster), input (client -> server, per-tick action), snapshot
# (server -> client, NetCodec-packed body state), and a small score_update
# for the HUD. Lives on an autoload per §1.3's derived decision ("All
# hot-path RPCs live on autoloads") even though these are scoped to
# whichever match happens to be running — a scene-node RPC target would
# need matching NodePaths across peers, which an autoload sidesteps
# entirely, and it's what lets NetworkedMatch itself stay a plain scene
# node with no networking-identity concerns of its own.
#
# Channel intent per §2.1: 0 reliable (match_config, score_update), 1
# unreliable-ordered (input), 2 unreliable-ordered (snapshot) — not yet
# verified against ENet's own reserved system channel offset (§2.1's own
# "verify empirically" hedge); if that turns out to matter these indices
# will need adjusting, not the RPC design itself.

const NetCodec = preload("res://scripts/net_codec.gd")

signal match_config_received(arena_path: String, peer_ids: PackedInt32Array, teams: PackedInt32Array, spawn_indices: PackedInt32Array)
signal input_received(peer_id: int, decoded: Dictionary)    # decoded: see NetCodec.unpack_input
signal snapshot_received(decoded: Dictionary)                # decoded: see NetCodec.unpack_snapshot
signal score_update_received(score: Dictionary)

# Input validation (multiplayer-todo.md §3.1 steps 2-3, task 3.4). Deliberately
# lives here rather than in NetworkedMatch: framing/rate abuse is a protocol-
# level concern independent of any particular match's roster/slot state, and
# this autoload already owns the RPC that receives the raw bytes.
#
# 60Hz * 1.5 + 20, per §3.1 step 2's own numbers.
const RATE_LIMIT_PACKETS_PER_SEC := 110
# "Same for a byte budget" (§3.1 step 2) — the worst-case legitimate packet
# is a full-redundancy input (INPUT_HEADER_SIZE + MAX_REDUNDANCY entries,
# the "40 B input" §2.3 sizes to), so the byte budget is just the packet
# budget scaled by that worst-case size — no separate constant to keep in
# sync by hand.
const RATE_LIMIT_BYTES_PER_SEC := RATE_LIMIT_PACKETS_PER_SEC * (NetCodec.INPUT_HEADER_SIZE + NetCodec.MAX_REDUNDANCY * NetCodec.INPUT_ENTRY_SIZE)
const RATE_LIMIT_WINDOW_MS := 1000
# Leaky-bucket excess tolerance, expressed in the same "N seconds' worth of
# budget" terms the original consecutive-streak design used. An adversarial
# review found that design — a streak counter that HARD-RESET to 0 on any
# single clean window — was trivially evaded by a duty-cycled flood (burst,
# then one clean window, repeat): reproduced sustaining ~33x the packet
# budget indefinitely with zero disconnect warnings. A leaky bucket doesn't
# care how the excess is distributed in time — see the window-roll logic
# below for how it accumulates and drains.
const RATE_LIMIT_EXCESS_PACKETS_TO_DISCONNECT := RATE_LIMIT_PACKETS_PER_SEC * 3
const RATE_LIMIT_EXCESS_BYTES_TO_DISCONNECT := RATE_LIMIT_BYTES_PER_SEC * 3
const MALFORMED_LIMIT_TO_DISCONNECT := 20


class _PeerInputState:
	var window_start_ms := 0
	var packets_this_window := 0
	var bytes_this_window := 0
	# Leaky bucket: grows by this window's actual total, drains by one
	# window's worth of budget, every window — regardless of whether that
	# window was itself over or under budget. A steady rate at or under
	# budget nets to zero forever (never accumulates); any sustained AVERAGE
	# above budget accumulates over time no matter how it's shaped into
	# bursts, unlike a streak counter a clean gap can reset to 0.
	var excess_packets := 0.0
	var excess_bytes := 0.0
	var malformed_count := 0


var _peer_input_state: Dictionary = {}   # peer_id -> _PeerInputState, server only

# Bandwidth (task 3.7's debug overlay): only the two 60Hz hot-path channels
# (input, snapshot) — match_config/score_update are low-frequency control
# messages, not what §2's byte-budget analysis or a live overlay cares
# about. Rolling per-second counters, recomputed opportunistically on each
# send/receive rather than on a timer — nothing needs the rate outside of
# an on-demand overlay read anyway. Use get_bytes_sent_per_sec() /
# get_bytes_received_per_sec() to READ these, not the raw fields directly
# — see those functions for why.
const BANDWIDTH_WINDOW_MS := 1000
var bytes_sent_per_sec := 0.0
var bytes_received_per_sec := 0.0
var _sent_window_start_ms := 0
var _sent_window_bytes := 0
var _received_window_start_ms := 0
var _received_window_bytes := 0


# An adversarial review found bytes_*_per_sec only ever gets recomputed
# INSIDE _track_sent()/_track_received() — i.e. only when traffic actually
# arrives — so if traffic stops entirely (right before a disconnect, or
# during exactly the kind of outage this overlay exists to diagnose), the
# last computed rate displays forever instead of decaying toward zero.
# Report zero once meaningfully more than one window has passed with
# nothing tracked, rather than trusting a stale field.
func get_bytes_sent_per_sec() -> float:
	if Time.get_ticks_msec() - _sent_window_start_ms > BANDWIDTH_WINDOW_MS * 2:
		return 0.0
	return bytes_sent_per_sec


func get_bytes_received_per_sec() -> float:
	if Time.get_ticks_msec() - _received_window_start_ms > BANDWIDTH_WINDOW_MS * 2:
		return 0.0
	return bytes_received_per_sec


func _ready() -> void:
	NetworkManager.client_disconnected.connect(func(peer_id: int) -> void: _peer_input_state.erase(peer_id))


func _track_sent(n: int) -> void:
	var now := Time.get_ticks_msec()
	if now - _sent_window_start_ms >= BANDWIDTH_WINDOW_MS:
		bytes_sent_per_sec = _sent_window_bytes * 1000.0 / maxf(1.0, float(now - _sent_window_start_ms))
		_sent_window_start_ms = now
		_sent_window_bytes = 0
	_sent_window_bytes += n


func _track_received(n: int) -> void:
	var now := Time.get_ticks_msec()
	if now - _received_window_start_ms >= BANDWIDTH_WINDOW_MS:
		bytes_received_per_sec = _received_window_bytes * 1000.0 / maxf(1.0, float(now - _received_window_start_ms))
		_received_window_start_ms = now
		_received_window_bytes = 0
	_received_window_bytes += n

# Server only: the last match_config actually sent, so a client whose own
# scene load (and therefore its match_config_received listener) finishes
# AFTER the server already broadcast can still get it — a one-shot
# broadcast alone is racy against however long the client takes to reach
# the point where it's listening, and Godot signals never buffer for a
# late connection. request_match_config() closes that race by turning
# delivery into "ask until you get it" instead of "hope you were already
# listening." Also covers a late joiner mid-match (Phase 5 will still need
# to add live match *state*, not just this static config, for that case).
var _last_match_config: Dictionary = {}


func send_match_config(arena_path: String, peer_ids: PackedInt32Array, teams: PackedInt32Array, spawn_indices: PackedInt32Array) -> void:
	_last_match_config = {
		"arena_path": arena_path, "peer_ids": peer_ids, "teams": teams, "spawn_indices": spawn_indices,
	}
	_match_config.rpc(arena_path, peer_ids, teams, spawn_indices)


func request_match_config() -> void:
	_request_match_config.rpc_id(1)


func send_input(bytes: PackedByteArray) -> void:
	_track_sent(bytes.size())
	# bytes is already fully packed (any timestamps it carries are already
	# fixed), so wrapping the dispatch itself is enough — task 2.8.
	NetSim.send(func() -> void: _recv_input.rpc_id(1, bytes), 1)


func send_snapshot(peer_id: int, bytes: PackedByteArray) -> void:
	_track_sent(bytes.size())
	NetSim.send(func() -> void: _snapshot.rpc_id(peer_id, bytes), peer_id)


func send_score_update(score: Dictionary) -> void:
	_score_update.rpc(score)


@rpc("authority", "call_remote", "reliable", 0)
func _match_config(arena_path: String, peer_ids: PackedInt32Array, teams: PackedInt32Array, spawn_indices: PackedInt32Array) -> void:
	match_config_received.emit(arena_path, peer_ids, teams, spawn_indices)


@rpc("any_peer", "call_remote", "reliable", 0)
func _request_match_config() -> void:
	if not multiplayer.is_server() or _last_match_config.is_empty():
		return
	var peer_id := multiplayer.get_remote_sender_id()
	_match_config.rpc_id(
		peer_id, _last_match_config["arena_path"], _last_match_config["peer_ids"],
		_last_match_config["teams"], _last_match_config["spawn_indices"]
	)


@rpc("any_peer", "call_remote", "unreliable_ordered", 1)
func _recv_input(bytes: PackedByteArray) -> void:
	if not multiplayer.is_server():
		return
	_track_received(bytes.size())
	var peer_id := multiplayer.get_remote_sender_id()

	var state: _PeerInputState = _peer_input_state.get(peer_id)
	if state == null:
		state = _PeerInputState.new()
		_peer_input_state[peer_id] = state

	# Rolling 1s window (§3.1 step 2). Rolled over lazily on the first
	# packet past the window boundary, not on a timer — this RPC only ever
	# runs when a packet actually arrives, so there's nothing to roll over
	# when nothing is arriving anyway.
	var now_ms := Time.get_ticks_msec()
	if now_ms - state.window_start_ms >= RATE_LIMIT_WINDOW_MS:
		state.excess_packets = maxf(0.0, state.excess_packets + float(state.packets_this_window) - float(RATE_LIMIT_PACKETS_PER_SEC))
		state.excess_bytes = maxf(0.0, state.excess_bytes + float(state.bytes_this_window) - float(RATE_LIMIT_BYTES_PER_SEC))
		state.window_start_ms = now_ms
		state.packets_this_window = 0
		state.bytes_this_window = 0
		if state.excess_packets > RATE_LIMIT_EXCESS_PACKETS_TO_DISCONNECT or state.excess_bytes > RATE_LIMIT_EXCESS_BYTES_TO_DISCONNECT:
			_disconnect_abusive_peer(peer_id, "input rate limit exceeded (excess_packets=%.0f excess_bytes=%.0f)" % [state.excess_packets, state.excess_bytes])
			return

	state.packets_this_window += 1
	state.bytes_this_window += bytes.size()
	if state.packets_this_window > RATE_LIMIT_PACKETS_PER_SEC or state.bytes_this_window > RATE_LIMIT_BYTES_PER_SEC:
		return   # over budget for the current window — drop, counted above at the next window roll

	# Framing (§3.1 step 3), validated before decoding — unpack_input can't
	# be trusted to catch this itself: StreamPeerBuffer silently zero-fills
	# past EOF rather than erroring (found during Phase 2's adversarial
	# review's hostile-client stress test), so a too-short or size-mismatched
	# payload would otherwise decode "successfully" into garbage actions
	# instead of being rejected.
	if bytes.size() < NetCodec.INPUT_HEADER_SIZE:
		_count_malformed(peer_id, state)
		return
	var count: int = bytes[5]   # type_version(1) + seq(4) precede count — see pack_input's own layout
	if count == 0 or count > NetCodec.MAX_REDUNDANCY or bytes.size() != NetCodec.INPUT_HEADER_SIZE + count * NetCodec.INPUT_ENTRY_SIZE:
		_count_malformed(peer_id, state)
		return

	var decoded := NetCodec.unpack_input(bytes)
	input_received.emit(peer_id, decoded)


func _count_malformed(peer_id: int, state: _PeerInputState) -> void:
	state.malformed_count += 1
	if state.malformed_count >= MALFORMED_LIMIT_TO_DISCONNECT:
		_disconnect_abusive_peer(peer_id, "too many malformed input packets (%d)" % state.malformed_count)


func _disconnect_abusive_peer(peer_id: int, reason: String) -> void:
	push_warning("MatchSim: disconnecting peer %d for abuse: %s" % [peer_id, reason])
	_peer_input_state.erase(peer_id)
	if multiplayer.multiplayer_peer is ENetMultiplayerPeer:
		multiplayer.multiplayer_peer.disconnect_peer(peer_id)


@rpc("authority", "call_remote", "unreliable_ordered", 2)
func _snapshot(bytes: PackedByteArray) -> void:
	_track_received(bytes.size())
	var decoded := NetCodec.unpack_snapshot(bytes)
	snapshot_received.emit(decoded)


@rpc("authority", "call_remote", "reliable", 0)
func _score_update(score: Dictionary) -> void:
	score_update_received.emit(score)