feat(clients): host/network split in every stats HUD (stats phase 2, client side)

Consumes the 0xCF host-timing plane (449a67c) on all four GUI clients: each keeps a bounded pending ring of receipt samples keyed by pts, matches the host's per-AU capture→sent reports against it, and the HUD equation becomes = host 3.1 + network 6.7 + decode 2.1 + display 2.3 falling back to the combined `= host+network …` term whenever no timing matched the window (old host / datagram loss) — same total, one split fewer, never a misleading zero. Apple additionally gains the split as the only equation line under the stage-1 fallback presenter (receipt is presenter-independent), a `nextHostTiming` wrapper with its own plane lock, and a unit-tested `HostNetworkSplitter`; Android extends the JNI stats array 16→18 doubles (0–15 unchanged); Windows/Linux thread the split through `Stats` into the HUD and the headless/debug logs. Docs updated: design/stats-unification.md Phase 2 → implemented (wire format, fallback semantics), and the docs-site matrix's Sunshine "Host processing latency" row is now a direct match (ours includes the paced send; avg vs p50). Verified here: linux client clippy -D warnings green on the live tree, windows stub check + hand-verified diff, android cargo-ndk arm64 check green, apple loopback test extended (needs the rebuilt xcframework + swift test on the mac). On-glass: pending on all platforms. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-03 21:31:49 +00:00
parent 8470419433
commit 69609945a3
19 changed files with 610 additions and 59 deletions
@@ -83,6 +83,9 @@ public final class PunktfunkConnection {
    /// Same role for the feedback drain thread (rumble + HID-output — two core planes,
    /// drained sequentially by one thread).
    private let feedbackLock = NSLock()
+    /// Same role for the host-timing (0xCF) puller — its own plane in the core, drained
+    /// non-blockingly by the app's 1 s stats tick (never contends with the blocking pullers).
+    private let statsLock = NSLock()

    /// Negotiated session mode (host-confirmed).
    public private(set) var width: UInt32 = 0
@@ -665,6 +668,40 @@ public final class PunktfunkConnection {
        }
    }

+    /// One per-AU host-timing report (0xCF): the host's capture→fully-sent duration for the
+    /// access unit whose `AccessUnit.ptsNs` equals `ptsNs` exactly. The stats consumer derives
+    /// `network = (receivedNs + clockOffsetNs − ptsNs) − hostUs` — the host/network split of the
+    /// HUD's `host+network` stage (design/stats-unification.md Phase 2).
+    public struct HostTiming: Sendable, Equatable {
+        /// The AU's capture stamp (host capture clock — matches the AU's `ptsNs`).
+        public let ptsNs: UInt64
+        /// Host capture→sent duration, µs.
+        public let hostUs: UInt32
+    }
+
+    /// Pull the next per-AU host timing; nil on timeout, throws `.closed` once the session
+    /// ended. Best-effort plane: an older host never emits any — keep showing the combined
+    /// `host+network` stage then. Drain non-blockingly (`timeoutMs: 0`) from ONE stats
+    /// consumer (its own core plane, safe alongside the other pullers).
+    public func nextHostTiming(timeoutMs: UInt32 = 0) throws -> HostTiming? {
+        statsLock.lock()
+        defer { statsLock.unlock() }
+        guard let h = liveHandle() else { throw PunktfunkClientError.closed }
+
+        var out = PunktfunkHostTiming()
+        let rc = punktfunk_connection_next_host_timing(h, &out, timeoutMs)
+        switch rc {
+        case statusOK:
+            return HostTiming(ptsNs: out.pts_ns, hostUs: out.host_us)
+        case statusNoFrame:
+            return nil
+        case statusClosed:
+            throw PunktfunkClientError.closed
+        default:
+            throw PunktfunkClientError.status(rc)
+        }
+    }
+
    /// Send one input event (delivered to the host as a QUIC datagram). Thread-safe;
    /// silently dropped after close.
    public func send(_ event: PunktfunkInputEvent) {
@@ -684,10 +721,12 @@ public final class PunktfunkConnection {
        pumpLock.lock() // pullers exit at their next poll boundary, releasing these
        audioLock.lock()
        feedbackLock.lock()
+        statsLock.lock()
        abiLock.lock()
        let h = handle
        handle = nil
        abiLock.unlock()
+        statsLock.unlock()
        feedbackLock.unlock()
        audioLock.unlock()
        pumpLock.unlock()
@@ -0,0 +1,88 @@
+// Splits the unified stats model's `host+network` stage (capture→received) into its `host`
+// (capture→fully-sent, reported per AU by the host on the 0xCF plane) and `network`
+// (the remainder) terms — design/stats-unification.md Phase 2.
+//
+// Receipt samples are recorded per frame from the pump path; host timings are matched to them
+// by exact pts (the 0xCF datagram carries the AU's own `pts_ns`). Best-effort by construction:
+// a lost 0xCF datagram, an FEC-dropped AU, or an old host that never emits the plane simply
+// contributes no split sample — the HUD then keeps the combined `host+network` line. NSLock
+// rather than an actor — the receipt writer is the non-async pump path (same pattern as
+// LatencyMeter/FrameMeter).
+
+import Foundation
+
+/// Per-frame `host` / `network` sampler: `recordReceipt` at AU receipt (pts + the combined
+/// capture→received interval), `noteHostTiming` per drained 0xCF report, `drain` the window's
+/// p50s once a second. The pending ring is bounded (drop-oldest) so an old host — receipts
+/// forever, timings never — costs a fixed ~4 KB, not growth.
+public final class HostNetworkSplitter: @unchecked Sendable {
+    private let lock = NSLock()
+    /// Received AUs awaiting their 0xCF host timing: (pts, combined capture→received µs).
+    private var pending: [(ptsNs: UInt64, combinedUs: Int64)] = []
+    private var hostUsSamples: [Int64] = []
+    private var networkUsSamples: [Int64] = []
+    /// ~1 s of frames at 240 fps; beyond it the oldest receipt can no longer expect a match.
+    private static let pendingCap = 256
+
+    public init() {}
+
+    /// Record one frame at receipt. `ptsNs` is the host capture clock (the AU's pts),
+    /// `receivedNs` the client `CLOCK_REALTIME` receipt instant (`AccessUnit.receivedNs`),
+    /// `offsetNs` the connect-time host−client clock offset (0 = uncorrected). Same
+    /// absurd-value clamp as LatencyMeter — a sample it would drop must not linger here.
+    public func recordReceipt(ptsNs: UInt64, receivedNs: Int64, offsetNs: Int64) {
+        let combinedNs = receivedNs &+ offsetNs &- Int64(bitPattern: ptsNs)
+        guard combinedNs > 0, combinedNs < 10_000_000_000 else { return }
+        lock.lock()
+        pending.append((ptsNs: ptsNs, combinedUs: combinedNs / 1000))
+        if pending.count > Self.pendingCap {
+            pending.removeFirst(pending.count - Self.pendingCap)
+        }
+        lock.unlock()
+    }
+
+    /// Match one host timing (0xCF) to its receipt: `host` = the reported capture→sent,
+    /// `network` = the combined interval minus it, floored at 0 (the terms tile per frame; a
+    /// slightly-off skew offset must not produce a negative wire time). Unmatched timings —
+    /// the AU was FEC-dropped, or its receipt raced this drain — are simply skipped.
+    public func noteHostTiming(ptsNs: UInt64, hostUs: UInt32) {
+        lock.lock()
+        defer { lock.unlock() }
+        guard let i = pending.firstIndex(where: { $0.ptsNs == ptsNs }) else { return }
+        let combinedUs = pending.remove(at: i).combinedUs
+        hostUsSamples.append(Int64(hostUs))
+        networkUsSamples.append(max(0, combinedUs - Int64(hostUs)))
+    }
+
+    public struct Split: Sendable {
+        public let hostP50Ms: Double
+        public let networkP50Ms: Double
+        public let count: Int
+    }
+
+    /// The window's p50s since the last drain, then reset (matched samples only; the pending
+    /// ring survives — a receipt may still match a timing drained next tick). `nil` when no
+    /// timing matched in the interval — the caller falls back to the combined stage.
+    public func drain() -> Split? {
+        lock.lock()
+        let host = hostUsSamples.sorted()
+        let network = networkUsSamples.sorted()
+        hostUsSamples.removeAll(keepingCapacity: true)
+        networkUsSamples.removeAll(keepingCapacity: true)
+        lock.unlock()
+        guard !host.isEmpty else { return nil }
+        func p50(_ sorted: [Int64]) -> Double {
+            Double(sorted[min(sorted.count / 2, sorted.count - 1)]) / 1000.0 // µs → ms
+        }
+        return Split(hostP50Ms: p50(host), networkP50Ms: p50(network), count: host.count)
+    }
+
+    /// Forget everything (pending receipts + window) — a fresh connection starts clean.
+    public func reset() {
+        lock.lock()
+        pending.removeAll()
+        hostUsSamples.removeAll()
+        networkUsSamples.removeAll()
+        lock.unlock()
+    }
+}