mirror of
https://github.com/jcreek/CosmicClash.git
synced 2026-09-10 16:04:04 +00:00
Josh Creek
75f485667b
Closes Phase 4's outstanding action-sequence-correctness invariant, then fixes two server-side bugs an adversarial review of that work uncovered. Server simulation, bot observations, collision resources and tick rate are unchanged: the server_physics_parity trace is byte-for-byte identical to HEAD across 360 ticks including both ships' full observation vectors. 4.11 - prediction history filed under the ISSUING sequence _send_local_input filed each post-step predicted state under the timeline's estimate of the sequence the server would consume this tick, trailing issuance by input_lead. The body had integrated the intent issued under _input_seq, so predicted[S] held "state after the intent from now" while the server's authority for S is "state after action(S)". They agree only while the stick is still. Filing under _input_seq costs nothing: which action the ship uses is decided in LocalNetShipController.get_action() and is untouched. Every prior Phase 4 gate held its input steady, and a steady input cannot falsify a sequence label - the 60s runs honestly reported marker=0/3784. New --exercise-input-transitions role toggles thrust every 6 ticks; it is the only gate that can catch a label regression. Verified non-vacuous: the old label fails it at 50%. 4.12 - issued-but-unsimulated sequences, and the release path An attack (delta > 1) issues and sends several sequences for one local physics step. Those gap sequences had no recorded prediction, so a server ack of one reported missing_not_recorded - indistinguishable from ring loss, costing a teleport and resync suppression several times a minute. They are now recorded stateless via record_unsimulated() and answered with a new "skip" decision mode. Free-flight hard snaps: 25/8/4 -> 0/0/0. A release (delta == 0) re-recorded at the unchanged _input_seq, filing the current intent under a sequence that went out carrying a different action; LocalInputTimeline deliberately refuses to mutate an issued sequence, so the ring contradicted the wire. Recording is now skipped on release ticks. 4.13 - two Phase 3 bugs silently killing player input (a) InputJitterBuffer.consume() advanced last_applied_seq on every tick including a starve. Since ingest() discards seq <= last_applied_seq, one starve on a sequence the client had not sent yet stranded the stream one ahead of arrivals permanently - both sides advancing in lockstep, every honest packet discarded on arrival. The client's own input_lead release is enough to trigger it, so input died for ~30 ticks roughly every 6.5s on a clean LAN. Now only gives up on a sequence once strictly newer data proves it lost. Silent-client stall and ring-overflow resync are unchanged. (b) The seq-range guard bounded incoming seq against highest_ingested_seq, which only advances inside ingest(), which that guard gates. After a ~2s host hitch every packet was rejected forever with no diagnostic (600+ consecutive rejections reproduced via SIGSTOP). Third iteration of this guard; each previous version bounded against a value only the accepted path could advance. Adds an escape after 10 consecutive rejections, which grants an attacker nothing the rate limiter does not already bound. (c) The transitions gate reported PASS at 3.76% while input was completely dead, because suppression stops _record_metrics - a worse outage yields fewer samples and a LOWER rate. Now scales the required sample count with run length and asserts the wire's server_stalled bit. Reverting both fixes makes it fail at samples 292/600, server_stalled=true, input_lead=12. Fixing (a) also explained a residual the review had already traced: 151 of 151 action-marker mismatches were the server repeating a stale action on a starve, not a prediction defect. Marker is now 0.00% in all three conditions (was 1.7-2.5%), and free-flight p99 improved to 0.141/0.168/0.154m from 0.170/0.176/0.184m. Two pre-existing test defects fixed alongside: the ball gate asserted RTT-masking on a link with no RTT (flaked 2 in 5; now asserted only at rtt >= 20ms, 5/5 under latency), and the two-bot CI compared scores across a 3-5s window (now polls the scores the server actually held; note score_changed is emitted only on the client path). QA: 72 unit tests; 60s free-flight at LAN/80+-20ms/5% loss; transition gate in all three; 2.0s and 3.5s host-freeze recovery; ball contact x5; two-bot CI x3; all three abuse roles; net/match_net/clock/lobby smokes. Phase 4 sign-off still pending a human playtest at ~100ms RTT - the milestone asks how it feels, which no gate here answers.
88 lines
4.4 KiB
GDScript
88 lines
4.4 KiB
GDScript
extends CanvasLayer
|
|
|
|
# Autoload: toggleable network debug overlay (F4 by default — see
|
|
# toggle_net_overlay in project.godot's [input]). Read-only against
|
|
# NetworkManager's clock state (task 1.8). Mirrors perf_overlay.gd's pattern
|
|
# — headless-guarded, hidden by default, no gameplay-state writes.
|
|
|
|
var _label: Label
|
|
|
|
|
|
func _ready() -> void:
|
|
if DisplayServer.get_name() == "headless":
|
|
set_process(false)
|
|
return
|
|
layer = 100
|
|
_label = Label.new()
|
|
_label.add_theme_font_size_override("font_size", 14)
|
|
_label.add_theme_color_override("font_color", Color(0.5, 0.8, 1.0))
|
|
_label.add_theme_color_override("font_shadow_color", Color(0, 0, 0, 0.85))
|
|
_label.add_theme_constant_override("shadow_offset_x", 1)
|
|
_label.add_theme_constant_override("shadow_offset_y", 1)
|
|
_label.position = Vector2(12, 90)
|
|
_label.visible = false
|
|
add_child(_label)
|
|
|
|
|
|
func _unhandled_input(event: InputEvent) -> void:
|
|
if event.is_action_pressed("toggle_net_overlay") and _label:
|
|
_label.visible = not _label.visible
|
|
return
|
|
if not _label or not _label.visible or not (event is InputEventKey) or not event.pressed or event.echo:
|
|
return
|
|
var game := get_tree().get_first_node_in_group("game")
|
|
if game == null or not game.has_method("adjust_prediction_tuning"):
|
|
return
|
|
# Client-only live tuning: [/] threshold, -/= visual decay, ,/. visual
|
|
# offset, P present-time A/B. Deliberately no project input actions: these
|
|
# diagnostics never enter ShipAction or server/controller code.
|
|
match event.keycode:
|
|
KEY_BRACKETLEFT: game.adjust_prediction_tuning(-0.1)
|
|
KEY_BRACKETRIGHT: game.adjust_prediction_tuning(0.1)
|
|
KEY_MINUS: game.adjust_prediction_tuning(0.0, -0.01)
|
|
KEY_EQUAL: game.adjust_prediction_tuning(0.0, 0.01)
|
|
KEY_COMMA: game.adjust_prediction_tuning(0.0, 0.0, -0.05)
|
|
KEY_PERIOD: game.adjust_prediction_tuning(0.0, 0.0, 0.05)
|
|
KEY_P: game.adjust_prediction_tuning(0.0, 0.0, 0.0, true)
|
|
|
|
|
|
func _process(_delta: float) -> void:
|
|
if not _label or not _label.visible:
|
|
return
|
|
if NetworkManager.is_server:
|
|
_label.text = "NET: server, %d peer(s) out %s in %s" % [
|
|
MatchNet.roster.size(), _format_kbps(MatchSim.get_bytes_sent_per_sec()), _format_kbps(MatchSim.get_bytes_received_per_sec()),
|
|
]
|
|
elif NetworkManager.is_client:
|
|
if NetworkManager.rtt_ms < 0.0:
|
|
_label.text = "NET: client, connecting (no clock sample yet)"
|
|
else:
|
|
# task 3.7: RTT, jitter, loss, buffer depth, snapshot age,
|
|
# bandwidth all live here now. Prediction error is intentionally
|
|
# absent — there is no client-side prediction until Phase 4, so
|
|
# there is nothing honest to show for it yet. STALLED shows the
|
|
# server's own InputJitterBuffer.stalled bit for this client's
|
|
# slot, round-tripped through the wire.
|
|
var stats := {}
|
|
var game := get_tree().get_first_node_in_group("game")
|
|
if game and game.has_method("get_net_debug_stats"):
|
|
stats = game.get_net_debug_stats()
|
|
var stalled_suffix := " STALLED" if stats.get("server_stalled", false) else ""
|
|
var prediction: Dictionary = stats.get("prediction", {})
|
|
_label.text = "NET: client RTT %.1fms jitter %.1fms offset %.1fms\nbuf depth %s (target %s) lead %s loss %.1f%% snap age %.1fms%s\npred pos p50/p95/p99 %.3f / %.3f / %.3fm\npred rot p50/p95/p99 %.2f / %.2f / %.2fdeg snaps %.2f/min\nremote residual p99 %.3fm / %.2fdeg A/B present=%s\ntune [/] pos %.2f -/= decay ,/. offset %.2f P toggle\nout %s in %s" % [
|
|
NetworkManager.rtt_ms, NetworkManager.jitter_ms, NetworkManager.clock_offset_ms,
|
|
str(stats.get("input_buffer_depth", -1)), str(stats.get("input_target_depth", "-")), str(stats.get("input_lead", "-")),
|
|
stats.get("snapshot_loss_pct", 0.0), stats.get("snapshot_age_ms", 0.0), stalled_suffix,
|
|
prediction.get("position_error_p50", 0.0), prediction.get("position_error_p95", 0.0), prediction.get("position_error_p99", 0.0),
|
|
prediction.get("rotation_error_p50", 0.0), prediction.get("rotation_error_p95", 0.0), prediction.get("rotation_error_p99", 0.0), prediction.get("hard_snap_rate_per_min", 0.0),
|
|
stats.get("remote_residual_position_p99", 0.0), stats.get("remote_residual_rotation_p99", 0.0), str(game.remote_visual_present_time_enabled if game else false),
|
|
prediction.get("position_threshold", 0.0), prediction.get("max_visual_offset", 0.0),
|
|
_format_kbps(MatchSim.get_bytes_sent_per_sec()), _format_kbps(MatchSim.get_bytes_received_per_sec()),
|
|
]
|
|
else:
|
|
_label.text = "NET: offline"
|
|
|
|
|
|
func _format_kbps(bytes_per_sec: float) -> String:
|
|
return "%.2f KB/s" % (bytes_per_sec / 1000.0)
|