feat(clients): unified stats vocabulary across every client + Moonlight comparison docs

One stat model everywhere (design/stats-unification.md): four measurement
points (capture/received/decoded/displayed), three stages that tile the
interval exactly, and a HUD that shows the addition explicitly —

  end-to-end 14.2 ms p50 · 19.8 p95 · capture→on-glass
  = host+network 9.8 + decode 2.1 + display 2.3

replacing each client's ad-hoc mix of overlapping absolutes (the Apple HUD's
three arrow lines that looked sequential but weren't), mean-vs-median decode
times (Windows/Linux), missing same-host-clock flags (Windows/Linux), and
three different names for the same capture→received measurement (probe's
"reassembled", Apple/Android's "client", Windows/Linux's post-decode "lat").

Per client: Apple threads receivedNs through the VT decode via the frame
refcon bit pattern so the decode stage exists at all (stage-1 fallback
honestly degrades to a capture→received headline); Windows carries
FrameTimes through the existing frame channel to the render thread and adds
e2e p50/p95 post-Present; Linux stamps received at AU pop and rides
decoded_ns on DecodedFrame to the paintable-set site; Android pairs receipt
stamps with MediaCodec output buffers via the codec's pts round-trip (JNI
stats array 14→16 doubles, indexes 0-13 unchanged). fps now uniformly counts
received AUs; lost/(received+lost) per window, hidden at zero.

docs-site gains "Understanding the Stats Overlay": what each line means, why
the equation only approximately sums (percentiles), and a line-by-line
Moonlight/Sunshine matrix — including that Moonlight has no end-to-end
number and its "network latency" is an ENet control RTT, so punktfunk's
headline must not be compared against any single Moonlight line.

Verified here: linux client + probe + core check/clippy/fmt green, android
native cargo-ndk arm64 check green. Pending: Windows CI + on-glass, swift
test on the mac, on-device Android.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

clients/android/app/src/main/kotlin/io/unom/punktfunk/StatsOverlay.kt

@@ -15,11 +15,13 @@ import io.unom.punktfunk.kit.NativeBridge
 import kotlin.math.roundToInt
 
 /**
- * The live stats overlay — mirrors the Apple client's HUD. Reads the 14-double layout from
+ * The live stats overlay — the unified HUD (`design/stats-unification.md`, Android v1: headline is
+ * `capture→decoded`, tiled by `host+network` + `decode`). Reads the 16-double layout from
  * [NativeBridge.nativeVideoStats]:
- * `[fps, mbps, latP50Ms, latP95Ms, latValid, skew, w, h, hz, dropped, bitDepth, colorPrimaries,
- * colorTransfer, chromaFormatIdc]`. The trailing four (present on a current native lib) describe the
- * negotiated video feed and render as a codec/depth/colour/chroma line; older layouts just omit it.
+ * `[fps, mbps, e2eP50Ms, e2eP95Ms, latValid, skew, w, h, hz, lost, bitDepth, colorPrimaries,
+ * colorTransfer, chromaFormatIdc, hostNetP50Ms, decodeP50Ms]`. Indexes 10–13 (present on a current
+ * native lib) describe the negotiated video feed and render as a codec/depth/colour/chroma line;
+ * 14/15 render as the stage equation; older layouts just omit those lines.
  */
 @Composable
 internal fun StatsOverlay(s: DoubleArray, modifier: Modifier = Modifier) {
@@ -29,7 +31,7 @@ internal fun StatsOverlay(s: DoubleArray, modifier: Modifier = Modifier) {
     val hz = s[8].toInt()
     val latValid = s[4] != 0.0
     val skew = s[5] != 0.0
-    val dropped = s[9].toLong()
+    val lost = s[9].toLong()
     Column(
         modifier = modifier
             .background(Color.Black.copy(alpha = 0.45f), RoundedCornerShape(6.dp))
@@ -50,17 +52,25 @@ internal fun StatsOverlay(s: DoubleArray, modifier: Modifier = Modifier) {
             )
         }
         if (latValid) {
-            val tag = if (skew) "" else " (same-host)"
+            val tag = if (skew) "" else " (same-host clock)"
             Text(
-                "capture→client ${"%.1f".format(s[2])}/${"%.1f".format(s[3])} ms p50/p95$tag",
+                "end-to-end ${"%.1f".format(s[2])} ms p50 · ${"%.1f".format(s[3])} p95 · capture→decoded$tag",
                 color = Color.White,
                 fontFamily = FontFamily.Monospace,
                 fontSize = 12.sp,
             )
+            if (s.size >= 16) {
+                Text(
+                    "= host+network ${"%.1f".format(s[14])} + decode ${"%.1f".format(s[15])}",
+                    color = Color.White,
+                    fontFamily = FontFamily.Monospace,
+                    fontSize = 12.sp,
+                )
+            }
         }
-        if (dropped > 0) {
+        if (lost > 0) {
             Text(
-                "dropped $dropped",
+                "lost $lost",
                 color = Color(0xFFFFB0B0),
                 fontFamily = FontFamily.Monospace,
                 fontSize = 12.sp,

clients/android/kit/src/main/kotlin/io/unom/punktfunk/kit/NativeBridge.kt

@@ -105,12 +105,14 @@ object NativeBridge {
 
     /**
      * Drain ~1 s of live decode stats for the on-stream HUD, or `null` when no decode thread runs.
-     * Returns 14 doubles:
-     * `[fps, mbps, latP50Ms, latP95Ms, latValid, skewCorrected, width, height, refreshHz, framesDropped,
-     * bitDepth, colorPrimaries, colorTransfer, chromaFormatIdc]`
-     * (the two flags are 1.0/0.0; the trailing four describe the negotiated video feed — bit depth
-     * 8/10, CICP primaries/transfer, and the HEVC chroma_format_idc 1=4:2:0 / 3=4:4:4). Poll ~1 Hz;
-     * each call resets the measurement window.
+     * Returns 16 doubles (unified stats spec, `design/stats-unification.md`):
+     * `[fps, mbps, e2eP50Ms, e2eP95Ms, latValid, skewCorrected, width, height, refreshHz, framesLost,
+     * bitDepth, colorPrimaries, colorTransfer, chromaFormatIdc, hostNetP50Ms, decodeP50Ms]`
+     * (the two flags are 1.0/0.0; indexes 2/3 are the end-to-end capture→decoded headline; 10–13
+     * describe the negotiated video feed — bit depth 8/10, CICP primaries/transfer, and the HEVC
+     * chroma_format_idc 1=4:2:0 / 3=4:4:4; 14/15 are the stage p50s tiling the headline —
+     * `host+network` = capture→received, `decode` = received→decoded). Poll ~1 Hz; each call
+     * resets the measurement window.
      */
     external fun nativeVideoStats(handle: Long): DoubleArray?
 

clients/android/native/src/decode.rs

@@ -9,16 +9,22 @@
 use ndk::data_space::DataSpace;
 use ndk::media::media_codec::{
     DequeuedInputBufferResult, DequeuedOutputBufferInfoResult, MediaCodec, MediaCodecDirection,
+    OutputBuffer,
 };
 use ndk::media::media_format::MediaFormat;
 use ndk::native_window::{FrameRateCompatibility, NativeWindow};
 use punktfunk_core::client::NativeClient;
 use punktfunk_core::error::PunktfunkError;
 use punktfunk_core::session::Frame;
+use std::collections::VecDeque;
 use std::sync::atomic::{AtomicBool, Ordering};
 use std::sync::Arc;
 use std::time::{Duration, Instant};
 
+/// Cap on the pts→received-timestamp map below: MediaCodec holds only a handful of frames in
+/// flight, so anything beyond this is stale (codec flushed / HUD toggled) and gets evicted.
+const IN_FLIGHT_CAP: usize = 64;
+
 /// The decode loop. Runs on the `pf-decode` thread until `shutdown` is set or the session closes.
 pub fn run(
     client: Arc<NativeClient>,
@@ -141,9 +147,14 @@ pub fn run(
     // climbs.
     let mut last_dropped = client.frames_dropped();
     let mut last_kf_req: Option<Instant> = None;
-    // Capture→client-receipt latency uses the negotiated host-minus-client clock offset (0 if the
-    // host didn't answer the skew handshake — then the HUD flags it "same-host").
+    // Skew-corrected latency stats (spec: design/stats-unification.md) use the negotiated
+    // host-minus-client clock offset (0 if the host didn't answer the skew handshake — then the
+    // HUD flags it "(same-host clock)").
     let clock_offset = client.clock_offset_ns;
+    // HUD stage split: receipt timestamps keyed by the pts we queue into the codec, so the decoded
+    // point (output-buffer dequeue — MediaCodec round-trips presentationTimeUs) can be paired back
+    // to its receipt for the `decode` stage. Only fed while the HUD is visible.
+    let mut in_flight: VecDeque<(u64, i128)> = VecDeque::new();
     // The dataspace we've signalled on the Surface so far (None = default/SDR). Set reactively once
     // the decoder reports an HDR stream (see `drain`); avoids re-applying every format event.
     let mut applied_ds: Option<DataSpace> = None;
@@ -164,15 +175,21 @@ pub fn run(
                             &p[..p.len().min(6)]
                         );
                     }
-                    // HUD stat: capture→client-receipt latency = client_now + (host−client) −
+                    // HUD stat, `received` point: host+network = client_now + (host−client) −
                     // capture_pts. Gated on the HUD being visible — `enabled` first so the hidden
-                    // steady state skips the wall-clock read and the lock entirely.
+                    // steady state skips the wall-clock read and the lock entirely. The receipt
+                    // stamp is also parked in `in_flight` (keyed by the pts the codec will echo on
+                    // the output buffer) for the decoded-point pairing in `drain`.
                     if stats.enabled() {
-                        let lat_ns =
-                            now_realtime_ns() + clock_offset as i128 - frame.pts_ns as i128;
+                        let received_ns = now_realtime_ns();
+                        let lat_ns = received_ns + clock_offset as i128 - frame.pts_ns as i128;
                         let lat_us = (lat_ns > 0 && lat_ns < 10_000_000_000)
                             .then_some((lat_ns / 1000) as u64);
-                        stats.note(frame.data.len(), lat_us, clock_offset != 0);
+                        stats.note_received(frame.data.len(), lat_us, clock_offset != 0);
+                        in_flight.push_back((frame.pts_ns / 1000, received_ns));
+                        if in_flight.len() > IN_FLIGHT_CAP {
+                            in_flight.pop_front(); // stale — codec never echoed it back
+                        }
                     }
                     pending = Some(frame);
                 }
@@ -202,7 +219,15 @@ pub fn run(
         } else {
             Duration::ZERO
         };
-        let (r, d) = drain(&codec, &window, &mut applied_ds, wait);
+        let (r, d) = drain(
+            &codec,
+            &window,
+            &mut applied_ds,
+            wait,
+            &stats,
+            &mut in_flight,
+            clock_offset,
+        );
         rendered += r;
         discarded += d;
 
@@ -330,11 +355,19 @@ fn feed(codec: &MediaCodec, au: &[u8], pts_us: u64) -> bool {
 /// the caller's input is blocked so the loop waits on decoder progress instead of busy-spinning.
 /// Returns `(rendered, discarded)`. Also reacts to `OutputFormatChanged` (which can interleave
 /// between buffers — handled without losing the held buffer) to signal HDR on the Surface.
+///
+/// Each dequeued buffer is also the HUD's `decoded` measurement point (rendered or not — the frame
+/// finished decoding either way): end-to-end = decoded + clock_offset − capture pts, and the
+/// `decode` stage pairs the buffer's echoed presentationTimeUs back to the receipt stamp in
+/// `in_flight` (single-clock local difference, no skew involved).
 fn drain(
     codec: &MediaCodec,
     window: &NativeWindow,
     applied_ds: &mut Option<DataSpace>,
     first_wait: Duration,
+    stats: &crate::stats::VideoStats,
+    in_flight: &mut VecDeque<(u64, i128)>,
+    clock_offset: i64,
 ) -> (u64, u64) {
     let mut held = None; // newest ready buffer so far, presented after the loop
     let mut discarded: u64 = 0;
@@ -343,6 +376,9 @@ fn drain(
         match codec.dequeue_output_buffer(wait) {
             Ok(DequeuedOutputBufferInfoResult::Buffer(buf)) => {
                 wait = Duration::ZERO; // only the first dequeue may block
+                if stats.enabled() {
+                    note_decoded(stats, in_flight, clock_offset, &buf);
+                }
                 if let Some(stale) = held.replace(buf) {
                     // A newer frame is ready — drop the held one without rendering.
                     if let Err(e) = codec.release_output_buffer(stale, false) {
@@ -392,6 +428,40 @@ fn drain(
     (rendered, discarded)
 }
 
+/// HUD `decoded` point for one dequeued output buffer: build the end-to-end (capture→decoded,
+/// skew-corrected, clamped to (0, 10 s)) and `decode` (received→decoded, single-clock local, ≥ 0)
+/// samples and hand them to [`crate::stats::VideoStats::note_decoded`]. The codec echoes the input
+/// `presentationTimeUs` on the output buffer, which keys the receipt stamp in `in_flight`; entries
+/// older than the echoed pts are evicted (decode order == input order here — low-latency, no
+/// B-frames — so anything before it was dropped inside the codec or stamped before a flush).
+fn note_decoded(
+    stats: &crate::stats::VideoStats,
+    in_flight: &mut VecDeque<(u64, i128)>,
+    clock_offset: i64,
+    buf: &OutputBuffer<'_>,
+) {
+    let pts_us = buf.info().presentation_time_us().max(0) as u64;
+    let decoded_ns = now_realtime_ns();
+    // Pair the echoed pts back to its receipt stamp, evicting stale (older) entries as we go.
+    let mut received_ns = None;
+    while let Some(&(p, r)) = in_flight.front() {
+        if p > pts_us {
+            break; // future frame — leave it for its own output buffer
+        }
+        in_flight.pop_front();
+        if p == pts_us {
+            received_ns = Some(r);
+            break;
+        }
+    }
+    // pts_us is the truncated frame.pts_ns/1000 we queued, so ×1000 re-approximates capture time
+    // to < 1 µs — negligible against the ms-scale figures shown.
+    let e2e_ns = decoded_ns + clock_offset as i128 - pts_us as i128 * 1000;
+    let e2e_us = (e2e_ns > 0 && e2e_ns < 10_000_000_000).then_some((e2e_ns / 1000) as u64);
+    let decode_us = received_ns.map(|r| ((decoded_ns - r).max(0) / 1000) as u64);
+    stats.note_decoded(e2e_us, decode_us);
+}
+
 /// Map the decoder's reported output colour to a BT.2020 HDR dataspace, or `None` for SDR. The
 /// integer values are the Android MediaFormat colour constants the NDK shares: COLOR_TRANSFER
 /// ST2084 = 6 (PQ/HDR10), HLG = 7; COLOR_RANGE FULL = 1, LIMITED = 2 (the host encodes limited).

clients/android/native/src/session/planes.rs

@@ -72,14 +72,16 @@ pub extern "system" fn Java_io_unom_punktfunk_kit_NativeBridge_nativeStopVideo(
     })
 }
 
-/// `NativeBridge.nativeVideoStats(handle): DoubleArray?` — drain ~1 s of decode stats for the HUD.
-/// Returns 14 doubles
-/// `[fps, mbps, latP50Ms, latP95Ms, latValid, skewCorrected, width, height, refreshHz, framesDropped,
-/// bitDepth, colorPrimaries, colorTransfer, chromaFormatIdc]`
-/// (the two flags are 1.0/0.0; the trailing four describe the negotiated video feed — see below), or
-/// `null` when no decode thread is running. Poll ~1 Hz from the UI; each call resets the measurement
-/// window. Not android-gated — pure `jni` + connector reads, so it links on the host build too
-/// (Kotlin only ever calls it on device).
+/// `NativeBridge.nativeVideoStats(handle): DoubleArray?` — drain ~1 s of decode stats for the HUD
+/// (unified stats spec, `design/stats-unification.md`). Returns 16 doubles
+/// `[fps, mbps, e2eP50Ms, e2eP95Ms, latValid, skewCorrected, width, height, refreshHz, framesLost,
+/// bitDepth, colorPrimaries, colorTransfer, chromaFormatIdc, hostNetP50Ms, decodeP50Ms]`
+/// (the two flags are 1.0/0.0; indexes 0–13 match the previous 14-double layout with the latency
+/// pair re-based from capture→received to the end-to-end capture→decoded headline; the two stage
+/// p50s tiling it — `host+network` = capture→received, `decode` = received→decoded — are appended
+/// at the end), or `null` when no decode thread is running. Poll ~1 Hz from the UI; each call
+/// resets the measurement window. Not android-gated — pure `jni` + connector reads, so it links on
+/// the host build too (Kotlin only ever calls it on device).
 #[no_mangle]
 pub extern "system" fn Java_io_unom_punktfunk_kit_NativeBridge_nativeVideoStats(
     env: JNIEnv,
@@ -98,11 +100,11 @@ pub extern "system" fn Java_io_unom_punktfunk_kit_NativeBridge_nativeVideoStats(
         let snap = h.stats.drain();
         let mode = h.client.mode();
         let color = h.client.color;
-        let buf: [f64; 14] = [
+        let buf: [f64; 16] = [
             snap.fps,
             snap.mbps,
-            snap.lat_p50_ms,
-            snap.lat_p95_ms,
+            snap.e2e_p50_ms,
+            snap.e2e_p95_ms,
             if snap.lat_valid { 1.0 } else { 0.0 },
             if snap.skew_corrected { 1.0 } else { 0.0 },
             mode.width as f64,
@@ -117,6 +119,9 @@ pub extern "system" fn Java_io_unom_punktfunk_kit_NativeBridge_nativeVideoStats(
             color.primaries as f64,
             color.transfer as f64,
             h.client.chroma_format as f64,
+            // Stage p50s tiling the end-to-end headline (appended to keep 0–13 index-compatible).
+            snap.hostnet_p50_ms,
+            snap.decode_p50_ms,
         ];
         let arr = match env.new_double_array(buf.len() as jsize) {
             Ok(a) => a,

clients/android/native/src/stats.rs

@@ -1,8 +1,11 @@
-//! Live decode stats for the on-stream HUD (mirrors the Apple client's stats overlay): FPS,
-//! receive throughput, and capture→client-receipt latency (p50/p95). The decode thread is the sole
-//! writer (`note` per access unit); the JNI accessor `nativeVideoStats` drains a snapshot ~1 Hz and
-//! resets the window. Sampling is gated on the HUD actually being visible (`set_enabled`, driven by
-//! `nativeSetVideoStatsEnabled`) so the hidden steady state costs one relaxed atomic load per frame.
+//! Live decode stats for the on-stream HUD, following the unified stats spec
+//! (`design/stats-unification.md`): FPS, receive throughput, and the Android v1 stage split —
+//! headline `end-to-end` = capture→decoded (p50/p95) tiled by `host+network` = capture→received
+//! and `decode` = received→decoded (stage p50s). The decode thread is the sole writer
+//! (`note_received` per access unit at receipt, `note_decoded` per decoder output buffer); the JNI
+//! accessor `nativeVideoStats` drains a snapshot ~1 Hz and resets the window. Sampling is gated on
+//! the HUD actually being visible (`set_enabled`, driven by `nativeSetVideoStatsEnabled`) so the
+//! hidden steady state costs one relaxed atomic load per frame.
 //! Pure `std` so it compiles on the host build too (the decode thread is android-only, but
 //! `SessionHandle` holds the shared handle unconditionally).
 
@@ -13,9 +16,9 @@ use std::time::Instant;
 /// Rolling per-window accumulator. Rates are computed over the actual elapsed wall-time at drain
 /// (robust to poll jitter), so a poll that lands at 0.9 s or 1.1 s still reports the right FPS.
 pub struct VideoStats {
-    /// HUD gate: `note` runs on the per-frame decode path, so while the overlay is hidden it (and
-    /// the caller's latency computation — see `enabled`) early-outs on this flag alone. Off until
-    /// Kotlin shows the HUD.
+    /// HUD gate: the samplers run on the per-frame decode path, so while the overlay is hidden
+    /// they (and the caller's latency computation — see `enabled`) early-out on this flag alone.
+    /// Off until Kotlin shows the HUD.
     enabled: AtomicBool,
     inner: Mutex<Inner>,
 }
@@ -24,23 +27,42 @@ struct Inner {
     window_start: Instant,
     frames: u64,
     bytes: u64,
-    /// capture→client-receipt latency samples for this window, in microseconds.
-    lat_us: Vec<u64>,
+    /// `end-to-end` = capture→decoded latency samples for this window, in microseconds
+    /// (skew-corrected clock base).
+    e2e_us: Vec<u64>,
+    /// `host+network` stage = capture→received samples, in microseconds (skew-corrected).
+    hostnet_us: Vec<u64>,
+    /// `decode` stage = received→decoded samples, in microseconds (client-local, single clock).
+    decode_us: Vec<u64>,
     /// Whether the host answered the clock-skew handshake (latency is cross-machine valid).
     skew_corrected: bool,
 }
 
-/// A drained, computed view of one window. `lat_valid` is false when no in-range latency sample
-/// landed (then p50/p95 are 0 and the HUD hides the latency line, exactly like the Apple client).
+/// A drained, computed view of one window. `lat_valid` is false when no in-range end-to-end sample
+/// landed (then the latency figures are 0 and the HUD hides the latency lines, exactly like the
+/// Apple client).
 pub struct Snapshot {
     pub fps: f64,
     pub mbps: f64,
-    pub lat_p50_ms: f64,
-    pub lat_p95_ms: f64,
+    /// Headline `end-to-end` (capture→decoded) percentiles, ms.
+    pub e2e_p50_ms: f64,
+    pub e2e_p95_ms: f64,
+    /// Stage p50s (ms): `host+network` (capture→received) and `decode` (received→decoded).
+    pub hostnet_p50_ms: f64,
+    pub decode_p50_ms: f64,
     pub lat_valid: bool,
     pub skew_corrected: bool,
 }
 
+/// Percentile over a sorted-in-place µs sample vec, in ms. 0.0 when empty.
+fn pctl_ms(sorted_us: &[u64], p: f64) -> f64 {
+    if sorted_us.is_empty() {
+        return 0.0;
+    }
+    let n = sorted_us.len();
+    sorted_us[((n as f64 * p) as usize).min(n - 1)] as f64 / 1000.0
+}
+
 impl VideoStats {
     pub fn new() -> VideoStats {
         VideoStats {
@@ -49,14 +71,16 @@ impl VideoStats {
                 window_start: Instant::now(),
                 frames: 0,
                 bytes: 0,
-                lat_us: Vec::with_capacity(256),
+                e2e_us: Vec::with_capacity(256),
+                hostnet_us: Vec::with_capacity(256),
+                decode_us: Vec::with_capacity(256),
                 skew_corrected: false,
             }),
         }
     }
 
     /// Whether the HUD wants samples. The decode thread checks this BEFORE building a latency
-    /// sample, so the per-frame wall-clock read is skipped too while hidden.
+    /// sample, so the per-frame wall-clock reads are skipped too while hidden.
     // Read only by the android-only decode thread; unreferenced on the host build — expected.
     #[cfg_attr(not(target_os = "android"), allow(dead_code))]
     pub fn enabled(&self) -> bool {
@@ -75,18 +99,21 @@ impl VideoStats {
             g.window_start = Instant::now();
             g.frames = 0;
             g.bytes = 0;
-            g.lat_us.clear();
+            g.e2e_us.clear();
+            g.hostnet_us.clear();
+            g.decode_us.clear();
         }
     }
 
-    /// Record one decoded access unit: its wire size and (if in range) its capture→client latency.
+    /// Record one received access unit: its wire size and (if in range) its capture→received
+    /// `host+network` stage sample. Receipt is the fps/goodput counting point per the spec.
     // Driven only by the android-only decode thread; unreferenced on the host build — expected.
     #[cfg_attr(not(target_os = "android"), allow(dead_code))]
-    pub fn note(&self, bytes: usize, lat_us: Option<u64>, skew_corrected: bool) {
+    pub fn note_received(&self, bytes: usize, hostnet_us: Option<u64>, skew_corrected: bool) {
         if !self.enabled.load(Ordering::Relaxed) {
             return; // HUD hidden — skip the lock (the caller already skipped the clock read)
         }
-        // Poison-proof: `note` runs per-frame on the decode thread, which has no catch_unwind —
+        // Poison-proof: this runs per-frame on the decode thread, which has no catch_unwind —
         // a panic elsewhere must not turn every later lock into a second panic (the counters
         // stay consistent regardless).
         let mut g = self
@@ -96,14 +123,37 @@ impl VideoStats {
         g.frames += 1;
         g.bytes += bytes as u64;
         g.skew_corrected = skew_corrected;
-        if let Some(l) = lat_us {
-            g.lat_us.push(l);
+        if let Some(l) = hostnet_us {
+            g.hostnet_us.push(l);
+        }
+    }
+
+    /// Record one decoded output frame: its capture→decoded `end-to-end` sample and its
+    /// received→decoded `decode` stage sample (either may be absent — e.g. the receipt stamp for
+    /// this pts predates the HUD being shown).
+    // Driven only by the android-only decode thread; unreferenced on the host build — expected.
+    #[cfg_attr(not(target_os = "android"), allow(dead_code))]
+    pub fn note_decoded(&self, e2e_us: Option<u64>, decode_us: Option<u64>) {
+        if !self.enabled.load(Ordering::Relaxed) {
+            return; // HUD hidden — skip the lock (the caller already skipped the clock read)
+        }
+        // Poison-proof for the same reason as `note_received`.
+        let mut g = self
+            .inner
+            .lock()
+            .unwrap_or_else(std::sync::PoisonError::into_inner);
+        if let Some(l) = e2e_us {
+            g.e2e_us.push(l);
+        }
+        if let Some(l) = decode_us {
+            g.decode_us.push(l);
         }
     }
 
     /// Compute the window's rates + latency percentiles, then reset for the next window.
     pub fn drain(&self) -> Snapshot {
-        // Poison-proof for the same reason as `note` — a poisoned window still drains fine.
+        // Poison-proof for the same reason as `note_received` — a poisoned window still drains
+        // fine.
         let mut g = self
             .inner
             .lock()
@@ -111,26 +161,25 @@ impl VideoStats {
         let elapsed = g.window_start.elapsed().as_secs_f64().max(1e-3);
         let fps = g.frames as f64 / elapsed;
         let mbps = g.bytes as f64 * 8.0 / 1_000_000.0 / elapsed;
-        let (p50, p95, valid) = if g.lat_us.is_empty() {
-            (0.0, 0.0, false)
-        } else {
-            g.lat_us.sort_unstable();
-            let n = g.lat_us.len();
-            let at = |p: f64| g.lat_us[((n as f64 * p) as usize).min(n - 1)] as f64 / 1000.0;
-            (at(0.50), at(0.95), true)
+        g.e2e_us.sort_unstable();
+        g.hostnet_us.sort_unstable();
+        g.decode_us.sort_unstable();
+        let snap = Snapshot {
+            fps,
+            mbps,
+            e2e_p50_ms: pctl_ms(&g.e2e_us, 0.50),
+            e2e_p95_ms: pctl_ms(&g.e2e_us, 0.95),
+            hostnet_p50_ms: pctl_ms(&g.hostnet_us, 0.50),
+            decode_p50_ms: pctl_ms(&g.decode_us, 0.50),
+            lat_valid: !g.e2e_us.is_empty(),
+            skew_corrected: g.skew_corrected,
         };
-        let skew = g.skew_corrected;
         g.window_start = Instant::now();
         g.frames = 0;
         g.bytes = 0;
-        g.lat_us.clear();
-        Snapshot {
-            fps,
-            mbps,
-            lat_p50_ms: p50,
-            lat_p95_ms: p95,
-            lat_valid: valid,
-            skew_corrected: skew,
-        }
+        g.e2e_us.clear();
+        g.hostnet_us.clear();
+        g.decode_us.clear();
+        snap
     }
 }

clients/apple/Sources/PunktfunkClient/ContentView.swift

@@ -333,8 +333,9 @@ struct ContentView: View {
                     onSessionEnd: { [weak model] in
                         Task { @MainActor in model?.sessionEnded() }
                     },
-                    presentMeter: model.presentLatency,
-                    presentTailMeter: model.presentTail
+                    endToEndMeter: model.endToEnd,
+                    decodeMeter: model.decodeStage,
+                    displayMeter: model.displayStage
                 )
                 .overlay(alignment: placement.alignment) {
                     if captureEnabled && hudEnabled {

clients/apple/Sources/PunktfunkClient/Screenshots/ScreenshotScenes.swift

@@ -170,7 +170,10 @@ private struct ShotHUD: View {
                 Text("5120×1440@240  240 fps  812.4 Mb/s")
                     .font(.system(.caption, design: .monospaced))
             }
-            Text("capture→client 1.3/2.1 ms p50/p95")
+            Text("end-to-end 2.9 ms p50 · 3.8 p95 · capture→on-glass")
+                .font(.system(.caption2, design: .monospaced))
+                .foregroundStyle(.secondary)
+            Text("= host+network 1.3 + decode 0.7 + display 0.9")
                 .font(.system(.caption2, design: .monospaced))
                 .foregroundStyle(.secondary)
             #if os(macOS)

clients/apple/Sources/PunktfunkClient/Session/SessionModel.swift

@@ -59,36 +59,50 @@ final class SessionModel: ObservableObject {
     @Published var fps = 0
     @Published var mbps = 0.0
     @Published var totalFrames = 0
-    /// Capture→client-receipt latency (ms), skew-corrected across machines via the connect-time
-    /// clock offset — p50/p95 for the HUD. `latencyValid` is false until the first sample drains
-    /// (and whenever no host frames arrived in the last interval). `latencySkewCorrected` = the host
+    /// The unified latency stages (design/stats-unification.md), ms per 1 s window. `host+network`
+    /// = capture→received, skew-corrected across machines via the connect-time clock offset: the
+    /// stage-2 HUD shows its p50 in the equation line; the stage-1 fallback shows p50/p95 as its
+    /// `capture→received` headline. `hostNetworkValid` is false until the first sample drains (and
+    /// whenever no host frames arrived in the last interval). `hostNetworkSkewCorrected` = the host
     /// answered the skew handshake (the number is cross-machine valid, not just same-host).
-    @Published var latencyP50Ms = 0.0
-    @Published var latencyP95Ms = 0.0
-    @Published var latencyValid = false
-    @Published var latencySkewCorrected = false
-    /// Capture→present (glass-to-glass, modulo the host render→capture term) — only the stage-2
-    /// presenter can stamp this (it owns decode + a CAMetalLayer/display-link present). Stays
-    /// invalid under stage-1, where the layer presents internally with no per-frame callback.
-    @Published var presentLatencyP50Ms = 0.0
-    @Published var presentLatencyP95Ms = 0.0
-    @Published var presentLatencyValid = false
-    @Published var presentLatencySkewCorrected = false
-    /// Decode-completion→present (the "present tail": ring wait + render + vsync) — the term the
-    /// stage-2 presenter exists to shorten. Both instants are client-side, so no skew applies.
-    @Published var presentTailP50Ms = 0.0
-    @Published var presentTailP95Ms = 0.0
-    @Published var presentTailValid = false
+    @Published var hostNetworkP50Ms = 0.0
+    @Published var hostNetworkP95Ms = 0.0
+    @Published var hostNetworkValid = false
+    @Published var hostNetworkSkewCorrected = false
+    /// End-to-end = capture→on-glass, measured directly per frame (never summed from the stages) —
+    /// the HUD headline. Only the stage-2 presenter can stamp it (it owns decode + a
+    /// CAMetalLayer/display-link present); stays invalid under stage-1, where the layer presents
+    /// internally with no per-frame callback.
+    @Published var endToEndP50Ms = 0.0
+    @Published var endToEndP95Ms = 0.0
+    @Published var endToEndValid = false
+    @Published var endToEndSkewCorrected = false
+    /// The client-local stage terms of the HUD's equation line (single clock, no skew; p50 only):
+    /// decode = received→decoded, display = decoded→on-glass (ring wait + render + vsync — the
+    /// term the stage-2 presenter exists to shorten).
+    @Published var decodeP50Ms = 0.0
+    @Published var decodeValid = false
+    @Published var displayP50Ms = 0.0
+    @Published var displayValid = false
+    /// Unrecoverable network frame drops in the last window (FEC couldn't rebuild them) and their
+    /// share of frames offered, `lost/(received+lost)`. The HUD hides the line while zero.
+    @Published var lostFrames = 0
+    @Published var lostPct = 0.0
     /// Mirrors StreamView's capture state (it owns the input capture; this drives the
     /// HUD's "click to capture" / "⌘⎋ releases" hint).
     @Published var mouseCaptured = false
 
     let meter = FrameMeter()
+    /// Capture→received (the host+network stage), fed per AU at receipt by the stream view's
+    /// onFrame — under both presenters.
     let latency = LatencyMeter()
-    /// Fed by the stage-2 presenter's display link (capture→present). Passed to StreamView.
-    let presentLatency = LatencyMeter()
-    /// Fed by the same present stamp (decode-completion→present). Passed to StreamView.
-    let presentTail = LatencyMeter()
+    /// The stage-2 meters, passed to StreamView: end-to-end (capture→on-glass, stamped at
+    /// present), decode (received→decoded), display (decoded→on-glass).
+    let endToEnd = LatencyMeter()
+    let decodeStage = LatencyMeter()
+    let displayStage = LatencyMeter()
+    /// Cumulative reassembler-drop counter at the last stats drain (per-window `lost` delta).
+    private var lastFramesDropped: UInt64 = 0
     private var statsTimer: Timer?
     private var audio: SessionAudio?
     private var gamepadCapture: GamepadCapture?
@@ -281,7 +295,12 @@ final class SessionModel: ObservableObject {
         phase = .idle
         fps = 0
         mbps = 0
-        latencyValid = false
+        hostNetworkValid = false
+        endToEndValid = false
+        decodeValid = false
+        displayValid = false
+        lostFrames = 0
+        lostPct = 0
         mouseCaptured = false
     }
 
@@ -321,6 +340,7 @@ final class SessionModel: ObservableObject {
     }
 
     private func startStatsTimer() {
+        lastFramesDropped = 0 // a fresh connection's cumulative drop counter starts at 0
         let timer = Timer(timeInterval: 1.0, repeats: true) { [weak self] _ in
             guard let self else { return }
             Task { @MainActor in
@@ -328,28 +348,41 @@ final class SessionModel: ObservableObject {
                 self.fps = frames
                 self.mbps = Double(bytes) * 8 / 1_000_000
                 self.totalFrames = total
+                // Per-window `lost` = the delta of the connector's cumulative reassembler-drop
+                // counter (0 after close — treat a rewind as no loss rather than underflowing).
+                let dropped = self.connection?.framesDropped() ?? 0
+                let lost = dropped >= self.lastFramesDropped
+                    ? Int(dropped - self.lastFramesDropped) : 0
+                self.lastFramesDropped = dropped
+                self.lostFrames = lost
+                self.lostPct = lost > 0 ? Double(lost) / Double(frames + lost) * 100 : 0
                 if let lat = self.latency.drain() {
-                    self.latencyP50Ms = lat.p50Ms
-                    self.latencyP95Ms = lat.p95Ms
-                    self.latencySkewCorrected = lat.skewCorrected
-                    self.latencyValid = true
+                    self.hostNetworkP50Ms = lat.p50Ms
+                    self.hostNetworkP95Ms = lat.p95Ms
+                    self.hostNetworkSkewCorrected = lat.skewCorrected
+                    self.hostNetworkValid = true
                 } else {
-                    self.latencyValid = false
+                    self.hostNetworkValid = false
                 }
-                if let p = self.presentLatency.drain() {
-                    self.presentLatencyP50Ms = p.p50Ms
-                    self.presentLatencyP95Ms = p.p95Ms
-                    self.presentLatencySkewCorrected = p.skewCorrected
-                    self.presentLatencyValid = true
+                if let e = self.endToEnd.drain() {
+                    self.endToEndP50Ms = e.p50Ms
+                    self.endToEndP95Ms = e.p95Ms
+                    self.endToEndSkewCorrected = e.skewCorrected
+                    self.endToEndValid = true
                 } else {
-                    self.presentLatencyValid = false
+                    self.endToEndValid = false
                 }
-                if let t = self.presentTail.drain() {
-                    self.presentTailP50Ms = t.p50Ms
-                    self.presentTailP95Ms = t.p95Ms
-                    self.presentTailValid = true
+                if let d = self.decodeStage.drain() {
+                    self.decodeP50Ms = d.p50Ms
+                    self.decodeValid = true
                 } else {
-                    self.presentTailValid = false
+                    self.decodeValid = false
+                }
+                if let d = self.displayStage.drain() {
+                    self.displayP50Ms = d.p50Ms
+                    self.displayValid = true
+                } else {
+                    self.displayValid = false
                 }
             }
         }

clients/apple/Sources/PunktfunkClient/Session/StreamHUDView.swift

@@ -1,5 +1,7 @@
-// The streaming overlay HUD: mode + fps/throughput, the capture→client (and, under the stage-2
-// presenter, capture→present) latency lines, the platform input hint, and disconnect.
+// The streaming overlay HUD: mode + fps/throughput, the unified latency lines
+// (design/stats-unification.md — end-to-end headline + the stage equation under stage-2, the
+// capture→received headline under the stage-1 fallback), the loss counter, the platform input
+// hint, and disconnect.
 
 import PunktfunkKit
 import SwiftUI
@@ -18,24 +20,32 @@ struct StreamHUDView: View {
                 Text("\(connection.width)×\(connection.height)@\(connection.refreshHz)  \(model.fps) fps  \(model.mbps, specifier: "%.1f") Mb/s")
                     .font(.system(.caption, design: .monospaced))
             }
-            if model.latencyValid {
-                // Capture→client-receipt (skew-corrected); excludes the layer's decode+present —
-                // see LatencyMeter. "(same-host)" when the host didn't answer the skew handshake.
-                Text("capture→client \(model.latencyP50Ms, specifier: "%.1f")/\(model.latencyP95Ms, specifier: "%.1f") ms p50/p95\(model.latencySkewCorrected ? "" : " (same-host)")")
+            if model.endToEndValid {
+                // Stage-2: the end-to-end headline (capture→on-glass, measured directly, skew-
+                // corrected) — "(same-host clock)" when the host didn't answer the skew handshake.
+                Text("end-to-end \(model.endToEndP50Ms, specifier: "%.1f") ms p50 · \(model.endToEndP95Ms, specifier: "%.1f") p95 · capture→on-glass\(model.endToEndSkewCorrected ? "" : " (same-host clock)")")
+                    .font(.system(.caption2, design: .monospaced))
+                    .foregroundStyle(.secondary)
+                // The equation: the three stages tiling the headline interval (per-window p50s —
+                // they only approximately sum to the directly-measured total).
+                if model.hostNetworkValid && model.decodeValid && model.displayValid {
+                    Text("= host+network \(model.hostNetworkP50Ms, specifier: "%.1f") + decode \(model.decodeP50Ms, specifier: "%.1f") + display \(model.displayP50Ms, specifier: "%.1f")")
+                        .font(.system(.caption2, design: .monospaced))
+                        .foregroundStyle(.secondary)
+                }
+            } else if model.hostNetworkValid {
+                // Stage-1 fallback presenter: the layer decodes + presents internally with no
+                // per-frame stamp, so the honest headline ends at receipt — and there is no
+                // equation line (host+network is the whole measured interval).
+                Text("capture→received \(model.hostNetworkP50Ms, specifier: "%.1f") ms p50 · \(model.hostNetworkP95Ms, specifier: "%.1f") p95\(model.hostNetworkSkewCorrected ? "" : " (same-host clock)")")
                     .font(.system(.caption2, design: .monospaced))
                     .foregroundStyle(.secondary)
             }
-            if model.presentLatencyValid {
-                // Capture→present (glass-to-glass, modulo host render→capture) — stage-2 presenter
-                // only; stage-1's layer presents internally with no per-frame stamp.
-                Text("capture→present \(model.presentLatencyP50Ms, specifier: "%.1f")/\(model.presentLatencyP95Ms, specifier: "%.1f") ms p50/p95\(model.presentLatencySkewCorrected ? "" : " (same-host)")")
-                    .font(.system(.caption2, design: .monospaced))
-                    .foregroundStyle(.secondary)
-            }
-            if model.presentTailValid {
-                // Decode→present (the client-local "present tail": ring wait + render + vsync) —
-                // the term the stage-2 presenter shortens; no skew applies (one clock).
-                Text("decode→present \(model.presentTailP50Ms, specifier: "%.1f")/\(model.presentTailP95Ms, specifier: "%.1f") ms p50/p95")
+            if model.lostFrames > 0 {
+                // Unrecoverable network drops this window; hidden while the link is clean.
+                // String(format:) rather than specifier interpolation: the literal % would
+                // otherwise land in the LocalizedStringKey's format string as a bogus conversion.
+                Text(String(format: "lost %d (%.1f%%)", model.lostFrames, model.lostPct))
                     .font(.system(.caption2, design: .monospaced))
                     .foregroundStyle(.secondary)
             }

clients/apple/Sources/PunktfunkClient/Settings/SettingsView+Sections.swift

@@ -310,10 +310,11 @@ extension SettingsView {
             Text("Video presenter · debug")
         } footer: {
             Text("Stage 2 (default) decodes explicitly and presents through Metal with a display "
-                + "link — it adds a capture→present (glass-to-glass) latency line in the HUD and "
-                + "self-recovers from decode stalls. Stage 1 feeds compressed video straight to the "
-                + "system display layer; it freezes on a lost HEVC reference frame, so it's a debug "
-                + "fallback only. Applies from the next session.")
+                + "link — it gives the HUD the end-to-end (capture→on-glass) headline with the "
+                + "host+network/decode/display stage equation and self-recovers from decode "
+                + "stalls. Stage 1 feeds compressed video straight to the system display layer; "
+                + "it freezes on a lost HEVC reference frame, so it's a debug fallback only. "
+                + "Applies from the next session.")
                 .font(.geist(12, relativeTo: .caption))
                 .foregroundStyle(.secondary)
         }

clients/apple/Sources/PunktfunkKit/Connection/PunktfunkConnection.swift

@@ -35,6 +35,10 @@ public struct AccessUnit: Sendable {
     public let ptsNs: UInt64
     public let frameIndex: UInt32
     public let flags: UInt32
+    /// Client `CLOCK_REALTIME` instant the AU was handed over by the core (post-FEC, decrypted)
+    /// — the **received** measurement point of design/stats-unification.md. The decode stage is
+    /// `decodedNs - receivedNs`, both client-local (no skew offset applies).
+    public let receivedNs: Int64
 }
 
 /// One Opus audio packet (48 kHz stereo, 5 ms frames) — decode with AVAudioConverter
@@ -419,9 +423,13 @@ public final class PunktfunkConnection {
         case statusOK:
             guard let base = frame.data, frame.len > 0 else { return nil }
             let data = Data(bytes: base, count: Int(frame.len)) // copy: ptr valid only until next call
+            var ts = timespec()
+            clock_gettime(CLOCK_REALTIME, &ts)
+            let receivedNs = Int64(ts.tv_sec) * 1_000_000_000 + Int64(ts.tv_nsec)
             return AccessUnit(
                 data: data, ptsNs: frame.pts_ns,
-                frameIndex: frame.frame_index, flags: frame.flags)
+                frameIndex: frame.frame_index, flags: frame.flags,
+                receivedNs: receivedNs)
         case statusNoFrame:
             return nil
         case statusClosed:

clients/apple/Sources/PunktfunkKit/Video/LatencyMeter.swift

@@ -1,23 +1,25 @@
-// Per-frame latency sampler for the live HUD: records capture->client-receipt latency and drains
-// percentiles on demand. NSLock rather than an actor — the writer is the non-async pump/arrival
-// path (same pattern as the app's FrameMeter).
+// Per-frame latency-stage sampler for the live HUD: records one interval per frame (an end
+// instant minus a start instant, both CLOCK_REALTIME ns) and drains percentiles on demand.
+// NSLock rather than an actor — the writers are the non-async pump/decode/present paths (same
+// pattern as the app's FrameMeter).
 
 import Foundation
 
-/// Samples the **capture->client-receipt** latency of each access unit and reports percentiles.
+/// Samples one **latency stage** per frame and reports percentiles. One instance per stage of the
+/// unified stats model (design/stats-unification.md):
 ///
-/// The latency is `now - pts_ns`, where `pts_ns` is the host's capture wall clock (the AU's pts) and
-/// `now` is the client's `CLOCK_REALTIME` instant the AU was received, shifted by the connect-time
-/// **clock-skew offset** (`PunktfunkConnection.clockOffsetNs`, host minus client) so the difference
-/// is valid across machines. `offsetNs == 0` means an old host that didn't answer the skew handshake
-/// (or genuinely synced clocks) — the number is then only meaningful same-host.
+/// - `host+network` = capture→received: `record(ptsNs:offsetNs:)` at AU receipt.
+/// - `decode` = received→decoded and `display` = decoded→displayed: client-local single-clock
+///   stages — `record(ptsNs:atNs:offsetNs:)` with the start instant as `ptsNs` and `offsetNs: 0`.
+/// - `end-to-end` = capture→displayed, measured directly (never summed from the stages):
+///   `record(ptsNs:atNs:offsetNs:)` at present.
 ///
-/// SCOPE (stage-1 presenter): this covers host capture -> encode -> FEC -> network -> reassembly ->
-/// decrypt -> handed to the presenter. It does **not** include the on-device VideoToolbox decode or
-/// the `AVSampleBufferDisplayLayer` present — that layer decodes and presents compressed samples
-/// internally with no per-frame callback. True decode->present (the full glass-to-glass) needs the
-/// stage-2 presenter (`VTDecompressionSession` decode-completion + `CAMetalLayer`/display-link
-/// present); this meter is the substrate it will extend.
+/// For the host-anchored intervals (capture→…) the sample is `end + offset - pts_ns`, where
+/// `pts_ns` is the host's capture wall clock (the AU's pts) and the connect-time **clock-skew
+/// offset** (`PunktfunkConnection.clockOffsetNs`, host minus client) makes the difference valid
+/// across machines. `offsetNs == 0` means an old host that didn't answer the skew handshake (or
+/// genuinely synced clocks) — the number is then only meaningful same-host, and the HUD tags the
+/// end-to-end line `(same-host clock)`.
 public final class LatencyMeter: @unchecked Sendable {
     private let lock = NSLock()
     private var samplesUs: [Int64] = []
@@ -34,12 +36,16 @@ public final class LatencyMeter: @unchecked Sendable {
         record(ptsNs: ptsNs, atNs: nowNs, offsetNs: offsetNs)
     }
 
-    /// Record one frame whose latency is `atNs + offsetNs - ptsNs` — an EXPLICIT client instant
-    /// rather than now. The stage-2 presenter uses this to stamp capture→present at the display
-    /// link's target present time (not the moment the present call ran). All in `CLOCK_REALTIME`.
+    /// Record one frame whose sample is `atNs + offsetNs - ptsNs` — an EXPLICIT end instant
+    /// rather than now. `ptsNs` is the stage's start point: the AU pts for the host-anchored
+    /// intervals, or a client stamp (receivedNs / decodedNs, with `offsetNs: 0`) for the local
+    /// decode/display stages. The stage-2 presenter stamps its present-side samples at the
+    /// display link's target present time (not the moment the present call ran). All in
+    /// `CLOCK_REALTIME`.
     public func record(ptsNs: UInt64, atNs: Int64, offsetNs: Int64) {
         let latNs = atNs &+ offsetNs &- Int64(bitPattern: ptsNs)
-        // Drop absurd values (a clock step, a wildly wrong offset, or garbage pts).
+        // Drop absurd values (a clock step, a wildly wrong offset, garbage pts, or a stage whose
+        // start stamp is missing/after its end) — samples are clamped to (0, 10 s).
         guard latNs > 0, latNs < 10_000_000_000 else { return }
         lock.lock()
         samplesUs.append(latNs / 1000)

clients/apple/Sources/PunktfunkKit/Video/SessionPresenter.swift

@@ -38,8 +38,9 @@ final class SessionPresenter {
     func start(
         connection: PunktfunkConnection,
         baseLayer: AVSampleBufferDisplayLayer,
-        presentMeter: LatencyMeter?,
-        presentTailMeter: LatencyMeter? = nil,
+        endToEndMeter: LatencyMeter?,
+        decodeMeter: LatencyMeter? = nil,
+        displayMeter: LatencyMeter? = nil,
         makeDisplayLink: (AnyObject, Selector) -> CADisplayLink,
         onFrame: (@Sendable (AccessUnit) -> Void)?,
         onSessionEnd: (@Sendable () -> Void)?
@@ -59,7 +60,8 @@ final class SessionPresenter {
         #endif
         if !forceStage1,
            let pipeline = Stage2Pipeline(
-               presentMeter: presentMeter, presentTailMeter: presentTailMeter) {
+               endToEndMeter: endToEndMeter, decodeMeter: decodeMeter,
+               displayMeter: displayMeter) {
             let metal = pipeline.layer
             // The opaque metal layer composites OVER the AVSampleBufferDisplayLayer base, which
             // sits idle (un-enqueued) in stage-2. contentsScale + frame are set in layout().

clients/apple/Sources/PunktfunkKit/Video/Stage2Pipeline.swift

@@ -1,7 +1,8 @@
 // Stage-2 presenter orchestrator: a pump thread pulls AUs → VideoDecoder; the decoder's async output
 // drops the newest decoded frame into a 1-slot ring; the hosting view's display link calls `renderTick`
-// once per vsync to draw + present the newest ready frame and stamp capture→present. Mirrors
-// StreamPump's lifecycle (one per start; cancel is permanent).
+// once per vsync to draw + present the newest ready frame and stamp the unified latency stages
+// (end-to-end capture→on-glass, plus the decode and display stage terms —
+// design/stats-unification.md). Mirrors StreamPump's lifecycle (one per start; cancel is permanent).
 //
 // Threading: the pump runs on its own thread; the decoder callback on a VT thread; `renderTick` +
 // `start`/`stop` on the MAIN thread (the view's CADisplayLink fires there). Only the ring (lock-guarded)
@@ -40,8 +41,8 @@ public final class Stage2Pipeline {
     private let ring = ReadyRing()
     private let presenter: MetalVideoPresenter
     private let decoder: VideoDecoder
-    private let presentMeter: LatencyMeter?
-    private let presentTailMeter: LatencyMeter?
+    private let endToEndMeter: LatencyMeter?
+    private let displayMeter: LatencyMeter?
     private let recovery = KeyframeRecovery()
     private var token = StopFlag()
     private var offsetNs: Int64 = 0
@@ -56,28 +57,41 @@ public final class Stage2Pipeline {
     /// The Metal layer the hosting view installs + sizes.
     public var layer: CAMetalLayer { presenter.layer }
 
-    /// `presentMeter` records capture→present (the glass-to-glass term); `presentTailMeter`
-    /// records decode-completion→present (the ring wait + render — the tail stage-2 exists to
-    /// shorten). Both optional: metering never gates the presenter choice. Returns nil if Metal
-    /// can't be set up (headless / no GPU) — caller falls back to the stage-1 presenter.
-    public init?(presentMeter: LatencyMeter?, presentTailMeter: LatencyMeter? = nil) {
+    /// Unified-stats meters (design/stats-unification.md): `endToEndMeter` records the headline
+    /// end-to-end (capture→on-glass, skew-corrected); `decodeMeter` the decode stage
+    /// (received→decoded); `displayMeter` the display stage (decoded→on-glass, the ring wait +
+    /// render + vsync — the tail stage-2 exists to shorten). All optional: metering never gates
+    /// the presenter choice. Returns nil if Metal can't be set up (headless / no GPU) — caller
+    /// falls back to the stage-1 presenter.
+    public init?(
+        endToEndMeter: LatencyMeter?,
+        decodeMeter: LatencyMeter? = nil,
+        displayMeter: LatencyMeter? = nil
+    ) {
         guard let presenter = MetalVideoPresenter.make() else { return nil }
         self.presenter = presenter
-        self.presentMeter = presentMeter
-        self.presentTailMeter = presentTailMeter
+        self.endToEndMeter = endToEndMeter
+        self.displayMeter = displayMeter
         let ring = ring
         let recovery = recovery
         self.decoder = VideoDecoder(
-            onDecoded: { ring.submit($0) },
+            onDecoded: { frame in
+                // Decode stage = received→decoded, both client CLOCK_REALTIME (offset 0 — no
+                // skew applies). Stamped at decode completion, so it covers every decoded frame,
+                // including ones the newest-wins ring drops before present.
+                decodeMeter?.record(
+                    ptsNs: UInt64(frame.receivedNs), atNs: frame.decodedNs, offsetNs: 0)
+                ring.submit(frame)
+            },
             // Async decode failure (a bad P-frame referencing a lost/corrupt IDR): the pump resets to
             // re-gate on the next IDR, and we ask the host to send one now (infinite GOP — it wouldn't
             // otherwise come soon). Throttled in KeyframeRecovery.
             onDecodeError: { _ in recovery.request() })
     }
 
-    /// Start pulling AUs into the decoder. MAIN THREAD. `onFrame` fires per AU at receipt (capture→client
-    /// meter, exactly as stage-1); `onSessionEnd` on close. `clockOffsetNs` (host minus client) makes the
-    /// present stamp cross-machine valid.
+    /// Start pulling AUs into the decoder. MAIN THREAD. `onFrame` fires per AU at receipt (the
+    /// host+network / capture→received meter, exactly as stage-1); `onSessionEnd` on close.
+    /// `clockOffsetNs` (host minus client) makes the end-to-end stamp cross-machine valid.
     public func start(
         connection: PunktfunkConnection,
         onFrame: (@Sendable (AccessUnit) -> Void)?,
@@ -174,14 +188,16 @@ public final class Stage2Pipeline {
     public func renderTick(targetPresentNs: Int64) {
         guard let frame = ring.take() else { return }
         let offsetNs = offsetNs
-        let presentMeter = presentMeter
-        let presentTailMeter = presentTailMeter
+        let endToEndMeter = endToEndMeter
+        let displayMeter = displayMeter
         let rendered = presenter.render(frame.pixelBuffer, isHDR: frame.isHDR) { presentedNs in
             let atNs = presentedNs ?? targetPresentNs
-            presentMeter?.record(ptsNs: frame.ptsNs, atNs: atNs, offsetNs: offsetNs)
-            // Present tail = decode-completion → on-glass. Both instants are client
-            // CLOCK_REALTIME, so no skew offset applies.
-            presentTailMeter?.record(ptsNs: UInt64(frame.decodedNs), atNs: atNs, offsetNs: 0)
+            // End-to-end = capture→on-glass, measured directly (skew-corrected via the
+            // connect-time clock offset) — the HUD headline.
+            endToEndMeter?.record(ptsNs: frame.ptsNs, atNs: atNs, offsetNs: offsetNs)
+            // Display stage = decoded → on-glass. Both instants are client CLOCK_REALTIME,
+            // so no skew offset applies.
+            displayMeter?.record(ptsNs: UInt64(frame.decodedNs), atNs: atNs, offsetNs: 0)
         }
         if !rendered { ring.putBack(frame) }
     }

clients/apple/Sources/PunktfunkKit/Video/Stage444Probe.swift

@@ -61,7 +61,7 @@ public enum Stage444Probe {
         guard created == noErr, let session else { return false }
         defer { VTDecompressionSessionInvalidate(session) }
 
-        let au = AccessUnit(data: data, ptsNs: 0, frameIndex: 0, flags: 0)
+        let au = AccessUnit(data: data, ptsNs: 0, frameIndex: 0, flags: 0, receivedNs: 0)
         guard let sample = AnnexB.sampleBuffer(au: au, format: format, codec: .hevc) else { return false }
 
         var produced: OSType = 0

clients/apple/Sources/PunktfunkKit/Video/VideoDecoder.swift

@@ -15,6 +15,10 @@ import VideoToolbox
 public struct ReadyFrame: @unchecked Sendable {
     /// Host capture clock (the AU's pts), in nanoseconds.
     public let ptsNs: UInt64
+    /// Client `CLOCK_REALTIME` instant the AU was received (`AccessUnit.receivedNs`, threaded
+    /// through the decode via the frame refcon), in nanoseconds. 0 when unknown (a caller that
+    /// didn't stamp receipt) — the decode-stage meter then drops the sample via its sanity guard.
+    public let receivedNs: Int64
     /// Client `CLOCK_REALTIME` instant decode completed, in nanoseconds.
     public let decodedNs: Int64
     /// The decoded image — 8-bit NV12 biplanar (SDR) or 10-bit P010 biplanar (HDR), Metal-compatible.
@@ -25,13 +29,16 @@ public struct ReadyFrame: @unchecked Sendable {
 }
 
 /// The C output callback can't capture context, so VideoToolbox hands it the refcon we set at
-/// session creation — a pointer back to the owning `VideoDecoder`.
+/// session creation — a pointer back to the owning `VideoDecoder`. The per-frame refcon carries
+/// the AU's `receivedNs` as a pointer bit pattern (a scalar smuggled through the C void*, never
+/// dereferenced) so the decode stage can be computed against decode-completion.
 private let decoderOutputCallback: VTDecompressionOutputCallback = {
-    refcon, _, status, _, imageBuffer, pts, _ in
+    refcon, frameRefcon, status, _, imageBuffer, pts, _ in
     guard let refcon else { return }
+    let receivedNs = frameRefcon.map { Int64(Int(bitPattern: $0)) } ?? 0
     Unmanaged<VideoDecoder>.fromOpaque(refcon)
         .takeUnretainedValue()
-        .handleDecoded(status: status, imageBuffer: imageBuffer, pts: pts)
+        .handleDecoded(status: status, imageBuffer: imageBuffer, pts: pts, receivedNs: receivedNs)
 }
 
 /// Owns a `VTDecompressionSession` rebuilt whenever the format description changes (every IDR /
@@ -112,7 +119,9 @@ public final class VideoDecoder: @unchecked Sendable {
             session,
             sampleBuffer: sample,
             flags: [._EnableAsynchronousDecompression],
-            frameRefcon: nil,
+            // The AU's receipt instant rides through as a bit pattern (nil for 0 — the output
+            // callback maps that back to 0); the callback needs it to stamp the decode stage.
+            frameRefcon: UnsafeMutableRawPointer(bitPattern: Int(au.receivedNs)),
             infoFlagsOut: &infoOut)
         lock.unlock()
         if status != noErr {
@@ -218,8 +227,11 @@ public final class VideoDecoder: @unchecked Sendable {
         return true
     }
 
-    /// VT thread. Stamp decode-completion and enqueue, or report the error.
-    fileprivate func handleDecoded(status: OSStatus, imageBuffer: CVImageBuffer?, pts: CMTime) {
+    /// VT thread. Stamp decode-completion and enqueue, or report the error. `receivedNs` is the
+    /// AU's receipt instant threaded through the frame refcon (0 = unknown).
+    fileprivate func handleDecoded(
+        status: OSStatus, imageBuffer: CVImageBuffer?, pts: CMTime, receivedNs: Int64
+    ) {
         guard status == noErr, let imageBuffer else {
             onDecodeError(status)
             return
@@ -242,6 +254,8 @@ public final class VideoDecoder: @unchecked Sendable {
             || fmt == kCVPixelFormatType_444YpCbCr10BiPlanarVideoRange
             || fmt == kCVPixelFormatType_444YpCbCr10BiPlanarFullRange
         onDecoded(
-            ReadyFrame(ptsNs: ptsNs, decodedNs: decodedNs, pixelBuffer: imageBuffer, isHDR: isHDR))
+            ReadyFrame(
+                ptsNs: ptsNs, receivedNs: receivedNs, decodedNs: decodedNs,
+                pixelBuffer: imageBuffer, isHDR: isHDR))
     }
 }

clients/apple/Sources/PunktfunkKit/Views/StreamView.swift

@@ -85,39 +85,45 @@ public struct StreamView: NSViewRepresentable {
     private let onCaptureChange: ((Bool) -> Void)?
     private let onFrame: (@Sendable (AccessUnit) -> Void)?
     private let onSessionEnd: (@Sendable () -> Void)?
-    private let presentMeter: LatencyMeter?
-    private let presentTailMeter: LatencyMeter?
+    private let endToEndMeter: LatencyMeter?
+    private let decodeMeter: LatencyMeter?
+    private let displayMeter: LatencyMeter?
 
     /// `onFrame`/`onSessionEnd` fire on the pump thread — hop to the main actor for UI.
     /// `captureEnabled: false` disables input capture entirely while UI (e.g. a trust
     /// prompt) is layered over the stream; flipping it to true auto-engages capture
     /// once. `onCaptureChange` (main thread) reports engage/release — drive the HUD's
-    /// "click to capture" / "⌘⎋ releases" hint with it. `presentMeter` records capture→present
-    /// and `presentTailMeter` decode→present when the stage-2 presenter is active.
+    /// "click to capture" / "⌘⎋ releases" hint with it. The meters record the unified latency
+    /// stages when the stage-2 presenter is active (design/stats-unification.md):
+    /// `endToEndMeter` capture→on-glass, `decodeMeter` received→decoded, `displayMeter`
+    /// decoded→on-glass.
     public init(
         connection: PunktfunkConnection,
         captureEnabled: Bool = true,
         onCaptureChange: ((Bool) -> Void)? = nil,
         onFrame: (@Sendable (AccessUnit) -> Void)? = nil,
         onSessionEnd: (@Sendable () -> Void)? = nil,
-        presentMeter: LatencyMeter? = nil,
-        presentTailMeter: LatencyMeter? = nil
+        endToEndMeter: LatencyMeter? = nil,
+        decodeMeter: LatencyMeter? = nil,
+        displayMeter: LatencyMeter? = nil
     ) {
         self.connection = connection
         self.captureEnabled = captureEnabled
         self.onCaptureChange = onCaptureChange
         self.onFrame = onFrame
         self.onSessionEnd = onSessionEnd
-        self.presentMeter = presentMeter
-        self.presentTailMeter = presentTailMeter
+        self.endToEndMeter = endToEndMeter
+        self.decodeMeter = decodeMeter
+        self.displayMeter = displayMeter
     }
 
     public func makeNSView(context: Context) -> StreamLayerView {
         let view = StreamLayerView()
         view.onCaptureChange = onCaptureChange
         view.captureEnabled = captureEnabled
-        view.presentMeter = presentMeter
-        view.presentTailMeter = presentTailMeter
+        view.endToEndMeter = endToEndMeter
+        view.decodeMeter = decodeMeter
+        view.displayMeter = displayMeter
         view.start(connection: connection, onFrame: onFrame, onSessionEnd: onSessionEnd)
         return view
     }
@@ -125,8 +131,9 @@ public struct StreamView: NSViewRepresentable {
     public func updateNSView(_ view: StreamLayerView, context: Context) {
         view.onCaptureChange = onCaptureChange
         view.captureEnabled = captureEnabled
-        view.presentMeter = presentMeter
-        view.presentTailMeter = presentTailMeter
+        view.endToEndMeter = endToEndMeter
+        view.decodeMeter = decodeMeter
+        view.displayMeter = displayMeter
         // SwiftUI reuses the NSView across state changes — repoint the pump only when the
         // connection identity actually changed.
         if view.connection !== connection {
@@ -141,10 +148,11 @@ public struct StreamView: NSViewRepresentable {
 
 public final class StreamLayerView: NSView {
     private let displayLayer = AVSampleBufferDisplayLayer()
-    /// Record capture→present / decode→present when the stage-2 presenter is active.
-    /// Consulted at start().
-    var presentMeter: LatencyMeter?
-    var presentTailMeter: LatencyMeter?
+    /// Record the unified latency stages (end-to-end / decode / display) when the stage-2
+    /// presenter is active. Consulted at start().
+    var endToEndMeter: LatencyMeter?
+    var decodeMeter: LatencyMeter?
+    var displayMeter: LatencyMeter?
     /// The shared presenter stack: stage-2 (CAMetalLayer sublayer + display link) with the
     /// stage-1 StreamPump → displayLayer path as the Metal-unavailable / DEBUG fallback.
     private let presenter = SessionPresenter()
@@ -571,8 +579,9 @@ public final class StreamLayerView: NSView {
         presenter.start(
             connection: connection,
             baseLayer: displayLayer,
-            presentMeter: presentMeter,
-            presentTailMeter: presentTailMeter,
+            endToEndMeter: endToEndMeter,
+            decodeMeter: decodeMeter,
+            displayMeter: displayMeter,
             makeDisplayLink: { displayLink(target: $0, selector: $1) },
             onFrame: onFrame,
             onSessionEnd: onSessionEnd)

clients/apple/Sources/PunktfunkKit/Views/StreamViewIOS.swift

@@ -50,8 +50,9 @@ public struct StreamView: UIViewControllerRepresentable {
     private let onCaptureChange: ((Bool) -> Void)?
     private let onFrame: (@Sendable (AccessUnit) -> Void)?
     private let onSessionEnd: (@Sendable () -> Void)?
-    private let presentMeter: LatencyMeter?
-    private let presentTailMeter: LatencyMeter?
+    private let endToEndMeter: LatencyMeter?
+    private let decodeMeter: LatencyMeter?
+    private let displayMeter: LatencyMeter?
 
     public init(
         connection: PunktfunkConnection,
@@ -59,24 +60,27 @@ public struct StreamView: UIViewControllerRepresentable {
         onCaptureChange: ((Bool) -> Void)? = nil,
         onFrame: (@Sendable (AccessUnit) -> Void)? = nil,
         onSessionEnd: (@Sendable () -> Void)? = nil,
-        presentMeter: LatencyMeter? = nil,
-        presentTailMeter: LatencyMeter? = nil
+        endToEndMeter: LatencyMeter? = nil,
+        decodeMeter: LatencyMeter? = nil,
+        displayMeter: LatencyMeter? = nil
     ) {
         self.connection = connection
         self.captureEnabled = captureEnabled
         self.onCaptureChange = onCaptureChange
         self.onFrame = onFrame
         self.onSessionEnd = onSessionEnd
-        self.presentMeter = presentMeter
-        self.presentTailMeter = presentTailMeter
+        self.endToEndMeter = endToEndMeter
+        self.decodeMeter = decodeMeter
+        self.displayMeter = displayMeter
     }
 
     public func makeUIViewController(context: Context) -> StreamViewController {
         let controller = StreamViewController()
         controller.onCaptureChange = onCaptureChange
         controller.captureEnabled = captureEnabled
-        controller.presentMeter = presentMeter
-        controller.presentTailMeter = presentTailMeter
+        controller.endToEndMeter = endToEndMeter
+        controller.decodeMeter = decodeMeter
+        controller.displayMeter = displayMeter
         controller.start(connection: connection, onFrame: onFrame, onSessionEnd: onSessionEnd)
         return controller
     }
@@ -84,8 +88,9 @@ public struct StreamView: UIViewControllerRepresentable {
     public func updateUIViewController(_ controller: StreamViewController, context: Context) {
         controller.onCaptureChange = onCaptureChange
         controller.captureEnabled = captureEnabled
-        controller.presentMeter = presentMeter
-        controller.presentTailMeter = presentTailMeter
+        controller.endToEndMeter = endToEndMeter
+        controller.decodeMeter = decodeMeter
+        controller.displayMeter = displayMeter
         if controller.connection !== connection {
             controller.start(connection: connection, onFrame: onFrame, onSessionEnd: onSessionEnd)
         }
@@ -101,10 +106,11 @@ public struct StreamView: UIViewControllerRepresentable {
 public final class StreamViewController: UIViewController {
     public private(set) var connection: PunktfunkConnection?
     private var observers: [NSObjectProtocol] = []
-    /// Record capture→present / decode→present when the stage-2 presenter is active.
-    /// Consulted at start().
-    var presentMeter: LatencyMeter?
-    var presentTailMeter: LatencyMeter?
+    /// Record the unified latency stages (end-to-end / decode / display) when the stage-2
+    /// presenter is active. Consulted at start().
+    var endToEndMeter: LatencyMeter?
+    var decodeMeter: LatencyMeter?
+    var displayMeter: LatencyMeter?
     /// The shared presenter stack: stage-2 (CAMetalLayer sublayer + display link) with the
     /// stage-1 StreamPump → displayLayer path as the Metal-unavailable / DEBUG fallback.
     private let presenter = SessionPresenter()
@@ -285,8 +291,9 @@ public final class StreamViewController: UIViewController {
         presenter.start(
             connection: connection,
             baseLayer: streamView.displayLayer,
-            presentMeter: presentMeter,
-            presentTailMeter: presentTailMeter,
+            endToEndMeter: endToEndMeter,
+            decodeMeter: decodeMeter,
+            displayMeter: displayMeter,
             makeDisplayLink: { CADisplayLink(target: $0, selector: $1) },
             onFrame: onFrame,
             onSessionEnd: onSessionEnd)

clients/apple/Tests/PunktfunkKitTests/LatencyMeterTests.swift

@@ -1,6 +1,10 @@
-// Unit tests for LatencyMeter: percentiles, the skew-corrected flag, reset-on-drain, and the
-// absurd-value guard. Latencies are constructed by stamping a pts a known interval in the past, so
-// the result is that interval plus the (tiny) clock advance between reads — asserted with tolerance.
+// Unit tests for LatencyMeter (one instance per unified-stats stage — see
+// design/stats-unification.md): percentiles, the skew-corrected flag, reset-on-drain, the
+// absurd-value guard, and the explicit-instant stage form (record(ptsNs:atNs:offsetNs:), used for
+// the client-local decode/display stages and the at-present end-to-end stamp). Receipt-path
+// latencies are constructed by stamping a pts a known interval in the past, so the result is that
+// interval plus the (tiny) clock advance between reads — asserted with tolerance; the explicit
+// form is exact.
 
 import Foundation
 import XCTest
@@ -38,6 +42,26 @@ final class LatencyMeterTests: XCTestCase {
         XCTAssertEqual(m.drain()?.skewCorrected, true)
     }
 
+    func testExplicitStageRecordIsExact() {
+        let m = LatencyMeter()
+        // A client-local stage (decode: received→decoded) — start instant as ptsNs, offset 0.
+        let receivedNs: Int64 = 1_000_000_000_000
+        m.record(ptsNs: UInt64(receivedNs), atNs: receivedNs + 3_000_000, offsetNs: 0)
+        guard let s = m.drain() else { return XCTFail("expected a sample") }
+        XCTAssertEqual(s.count, 1)
+        XCTAssertEqual(s.p50Ms, 3.0, "explicit instants make the sample exact")
+        XCTAssertFalse(s.skewCorrected, "local stages record with offset 0")
+    }
+
+    func testExplicitStageDropsNonPositiveInterval() {
+        let m = LatencyMeter()
+        // A stage whose start stamp is missing (0) or after its end must not pollute the window.
+        let decodedNs: Int64 = 1_000_000_000_000
+        m.record(ptsNs: 0, atNs: decodedNs, offsetNs: 0) // "start unknown" → > 10 s → dropped
+        m.record(ptsNs: UInt64(decodedNs + 1), atNs: decodedNs, offsetNs: 0) // negative → dropped
+        XCTAssertNil(m.drain())
+    }
+
     func testDropsAbsurdValues() {
         let m = LatencyMeter()
         let now = nowRealtimeNs()

clients/apple/Tests/PunktfunkKitTests/Stage444Tests.swift

@@ -31,7 +31,7 @@ final class Stage444Tests: XCTestCase {
         let data = Data(Probe444Blobs.au444_8bit)
         let format = try XCTUnwrap(
             AnnexB.formatDescription(fromIDR: data, codec: .hevc), "the 4:4:4 blob must yield a format description")
-        let au = AccessUnit(data: data, ptsNs: 7_000_000, frameIndex: 0, flags: 0)
+        let au = AccessUnit(data: data, ptsNs: 7_000_000, frameIndex: 0, flags: 0, receivedNs: 0)
 
         let box = FrameBox()
         let done = DispatchSemaphore(value: 0)

clients/apple/Tests/PunktfunkKitTests/VideoToolboxRoundTripTests.swift

@@ -38,7 +38,8 @@ final class VideoToolboxRoundTripTests: XCTestCase {
         XCTAssertEqual(AnnexB.avcc(from: annexB, codec: .hevc), avccSample)
 
         // 3) Sample buffer → real decoder → pixels.
-        let au = AccessUnit(data: annexB, ptsNs: 1_000_000, frameIndex: 0, flags: 0)
+        let au = AccessUnit(
+            data: annexB, ptsNs: 1_000_000, frameIndex: 0, flags: 0, receivedNs: 0)
         let sample = try XCTUnwrap(AnnexB.sampleBuffer(au: au, format: rebuilt, codec: .hevc))
 
         var session: VTDecompressionSession?
@@ -67,13 +68,14 @@ final class VideoToolboxRoundTripTests: XCTestCase {
     }
 
     /// Stage-2 decode half: the same known IDR through `VideoDecoder` — assert its async output
-    /// callback fires with a CVPixelBuffer of the right dimensions, the pts round-trips, and
-    /// decode-completion is stamped.
+    /// callback fires with a CVPixelBuffer of the right dimensions, the pts and the receipt stamp
+    /// round-trip (the latter rides the frame refcon), and decode-completion is stamped.
     func testVideoDecoderAsyncCallbackDeliversPixels() throws {
         let (formatDesc, avccSample) = try encodeOneHEVCKeyframe()
         let annexB = try annexBAU(formatDesc: formatDesc, avccSample: avccSample)
         let format = try XCTUnwrap(AnnexB.formatDescription(fromIDR: annexB, codec: .hevc))
-        let au = AccessUnit(data: annexB, ptsNs: 42_000_000, frameIndex: 0, flags: 0)
+        let au = AccessUnit(
+            data: annexB, ptsNs: 42_000_000, frameIndex: 0, flags: 0, receivedNs: 41_000_000)
 
         let box = FrameBox()
         let done = DispatchSemaphore(value: 0)
@@ -100,6 +102,8 @@ final class VideoToolboxRoundTripTests: XCTestCase {
         XCTAssertEqual(CVPixelBufferGetWidth(ready.pixelBuffer), width)
         XCTAssertEqual(CVPixelBufferGetHeight(ready.pixelBuffer), height)
         XCTAssertEqual(ready.ptsNs, 42_000_000, "pts round-trips through the decoder")
+        XCTAssertEqual(
+            ready.receivedNs, 41_000_000, "receivedNs round-trips through the frame refcon")
         XCTAssertGreaterThan(ready.decodedNs, 0, "decode-completion is stamped")
     }
 

clients/linux/src/session.rs

@@ -45,18 +45,40 @@ pub struct SessionParams {
     pub connect_timeout: Duration,
 }
 
+/// The session pump's share of the unified stats window (design/stats-unification.md):
+/// stream facts plus the two stages measured before the presenter. The frame consumer in
+/// `ui_stream` contributes the `display` stage and the end-to-end percentiles.
 #[derive(Clone, Copy, Default)]
 pub struct Stats {
+    /// AUs received (reassembled) per second, actual-elapsed-time denominator.
     pub fps: f32,
+    /// Received payload bytes × 8 / elapsed (goodput, excludes FEC overhead).
     pub mbps: f32,
+    /// p50 `host+network` stage: capture → received, host-clock corrected (ms).
+    pub host_net_ms: f32,
+    /// p50 `decode` stage: received → decoded, single-clock client-local (ms).
     pub decode_ms: f32,
-    /// Median capture→decoded latency over the last window (host-clock corrected).
-    pub latency_ms: f32,
+    /// Unrecoverable network frame drops this window, and their share of
+    /// received+lost (%). The OSD renders the counter line only when nonzero.
+    pub lost: u32,
+    pub lost_pct: f32,
     /// The decode path frames actually took this window (`"vaapi"`/`"software"`, empty
     /// until the first frame) — the OSD's trailing tag; tracks a mid-session fallback.
     pub decoder: &'static str,
 }
 
+/// Sort a window of µs samples in place and return `(p50, p95)` per the spec's index
+/// rules (`sorted[len/2]`, `sorted[min(len*95/100, len-1)]`); an empty window reads 0.
+pub fn window_percentiles(samples: &mut [u64]) -> (u64, u64) {
+    if samples.is_empty() {
+        return (0, 0);
+    }
+    samples.sort_unstable();
+    let p50 = samples[samples.len() / 2];
+    let p95 = samples[(samples.len() * 95 / 100).min(samples.len() - 1)];
+    (p50, p95)
+}
+
 pub enum SessionEvent {
     Connected {
         connector: Arc<NativeClient>,
@@ -219,13 +241,17 @@ fn pump(
     let mut window_start = Instant::now();
     let mut frames_n = 0u32;
     let mut bytes_n = 0u64;
-    let mut decode_us_sum = 0u64;
-    let mut lat_us: Vec<u64> = Vec::with_capacity(256);
+    // Stage windows (µs samples): `host+network` = capture→received (host-clock
+    // corrected), `decode` = received→decoded (client-local). p50 per 1 s window.
+    let mut hostnet_us: Vec<u64> = Vec::with_capacity(256);
+    let mut decode_us: Vec<u64> = Vec::with_capacity(256);
     // What actually decoded the last frame — a VAAPI failure demotes mid-session, so
     // this is read off each frame's image variant rather than fixed at startup.
     let mut dec_path: &'static str = "";
     // Loss recovery: watch the host→client unrecoverable-drop count and ask for an IDR when it climbs.
     let mut last_dropped = connector.frames_dropped();
+    // The stats window keeps its own drop cursor — the OSD shows the per-window delta.
+    let mut window_dropped = last_dropped;
     let mut last_kf_req: Option<Instant> = None;
 
     let end: Option<String> = loop {
@@ -237,7 +263,11 @@ fn pump(
         // every ~8–16 ms at 60–120 Hz anyway, so this rarely times out mid-stream).
         match connector.next_frame(Duration::from_millis(20)) {
             Ok(frame) => {
-                let t0 = Instant::now();
+                // The `received` point: AU fully reassembled, in hand, before decode.
+                let received_ns = now_ns();
+                // fps / goodput count every received AU (spec), decoded or not.
+                frames_n += 1;
+                bytes_n += frame.data.len() as u64;
                 match decoder.decode(&frame.data) {
                     Ok(Some(image)) => {
                         total_frames += 1;
@@ -252,18 +282,21 @@ fn pump(
                             };
                             tracing::info!(width = w, height = h, path, "first frame decoded");
                         }
-                        // Latency: our wall clock expressed in the host's capture clock,
-                        // minus the host-stamped capture pts (same math as client-rs).
-                        let lat = (now_ns() as i128 + clock_offset as i128 - frame.pts_ns as i128)
+                        // The `decoded` point — travels with the frame so the presenter
+                        // can measure its `display` stage against it.
+                        let decoded_ns = now_ns();
+                        // `host+network` stage: received expressed in the host's capture
+                        // clock, minus the host-stamped capture pts (clamped (0, 10 s)).
+                        let hn = (received_ns as i128 + clock_offset as i128 - frame.pts_ns as i128)
                             .max(0) as u64;
-                        if lat > 0 && lat < 10_000_000_000 {
-                            lat_us.push(lat / 1000);
+                        if hn > 0 && hn < 10_000_000_000 {
+                            hostnet_us.push(hn / 1000);
                         }
-                        decode_us_sum += t0.elapsed().as_micros() as u64;
-                        frames_n += 1;
-                        bytes_n += frame.data.len() as u64;
+                        // `decode` stage: received→decoded, single clock, no skew.
+                        decode_us.push(decoded_ns.saturating_sub(received_ns) / 1000);
                         let _ = frame_tx.force_send(DecodedFrame {
                             pts_ns: frame.pts_ns,
+                            decoded_ns,
                             image,
                         });
                     }
@@ -295,30 +328,36 @@ fn pump(
 
         if window_start.elapsed() >= Duration::from_secs(1) {
             let secs = window_start.elapsed().as_secs_f32();
-            lat_us.sort_unstable();
-            let p50 = lat_us.get(lat_us.len() / 2).copied().unwrap_or(0);
+            let (hn_p50, _) = window_percentiles(&mut hostnet_us);
+            let (dec_p50, _) = window_percentiles(&mut decode_us);
+            let lost = dropped.saturating_sub(window_dropped) as u32;
+            window_dropped = dropped;
             tracing::debug!(
                 fps = frames_n,
-                lat_p50_us = p50,
+                hostnet_p50_us = hn_p50,
+                decode_p50_us = dec_p50,
+                lost,
                 total_frames,
                 "stream window"
             );
             let _ = ev_tx.try_send(SessionEvent::Stats(Stats {
                 fps: frames_n as f32 / secs,
                 mbps: bytes_n as f32 * 8.0 / 1e6 / secs,
-                decode_ms: if frames_n > 0 {
-                    decode_us_sum as f32 / frames_n as f32 / 1000.0
+                host_net_ms: hn_p50 as f32 / 1000.0,
+                decode_ms: dec_p50 as f32 / 1000.0,
+                lost,
+                lost_pct: if lost > 0 {
+                    lost as f32 * 100.0 / (frames_n + lost) as f32
                 } else {
                     0.0
                 },
-                latency_ms: p50 as f32 / 1000.0,
                 decoder: dec_path,
             }));
             window_start = Instant::now();
             frames_n = 0;
             bytes_n = 0;
-            decode_us_sum = 0;
-            lat_us.clear();
+            hostnet_us.clear();
+            decode_us.clear();
         }
     };
 

clients/linux/src/ui_stream.rs

@@ -31,33 +31,63 @@ use std::time::{Duration, Instant};
 pub struct StreamPage {
     pub page: adw::NavigationPage,
     stats_label: gtk::Label,
-    /// Median capture→paintable-set latency (ms) over the frame consumer's last 1 s
-    /// window — written there, folded into the OSD on each `Stats` event.
-    present_ms: Rc<Cell<f32>>,
+    /// The frame consumer's share of the stats window (end-to-end percentiles + the
+    /// `display` stage) — written there each 1 s window, folded into the OSD on each
+    /// `Stats` event.
+    presented: Rc<PresentedStats>,
     /// The stream is HDR (PQ) right now — set by the frame consumer from each frame's
     /// signaling (the host can flip SDR↔HDR mid-session, in-band).
     hdr: Rc<Cell<bool>>,
+    /// `clock_offset_ns == 0`: the skew handshake didn't run (or same host) — the
+    /// end-to-end line carries the `(same-host clock)` flag (spec clock rules).
+    same_host: bool,
+    /// `W×H@Hz` for the OSD's first line — fixed at connect, per-session.
+    mode_line: String,
+}
+
+/// Presenter-side window results (design/stats-unification.md): end-to-end =
+/// capture→displayed measured directly (p50 + p95), `display` stage = decoded→displayed
+/// p50. All ms, refreshed once per 1 s window by the frame consumer.
+#[derive(Default)]
+struct PresentedStats {
+    e2e_p50_ms: Cell<f32>,
+    e2e_p95_ms: Cell<f32>,
+    display_ms: Cell<f32>,
 }
 
 impl StreamPage {
+    /// Render the canonical unified-stats OSD (design/stats-unification.md — Linux
+    /// endpoint is paintable-set, headline reads `capture→displayed`).
     pub fn update_stats(&self, s: Stats) {
-        let mut line = format!(
-            "{:.0} fps · {:.1} Mbit/s · dec {:.1} ms · lat {:.1} ms · present {:.1} ms",
-            s.fps,
-            s.mbps,
-            s.decode_ms,
-            s.latency_ms,
-            self.present_ms.get()
-        );
+        let mut line1 = format!("{} · {:.0} fps · {:.1} Mb/s", self.mode_line, s.fps, s.mbps);
         // Which decoder actually ran this window (vaapi/software) — tracks a fallback.
         if !s.decoder.is_empty() {
-            line.push_str(" · ");
-            line.push_str(s.decoder);
+            line1.push_str(" · ");
+            line1.push_str(s.decoder);
         }
         if self.hdr.get() {
-            line.push_str(" · HDR");
+            line1.push_str(" · HDR");
         }
-        self.stats_label.set_text(&line);
+        let mut text = format!(
+            "{line1}\n\
+             end-to-end {:.1} ms p50 · {:.1} p95 · capture→displayed{}\n\
+             = host+network {:.1} + decode {:.1} + display {:.1}",
+            self.presented.e2e_p50_ms.get(),
+            self.presented.e2e_p95_ms.get(),
+            if self.same_host {
+                " (same-host clock)"
+            } else {
+                ""
+            },
+            s.host_net_ms,
+            s.decode_ms,
+            self.presented.display_ms.get(),
+        );
+        // Counters — only rendered when nonzero this window.
+        if s.lost > 0 {
+            text.push_str(&format!("\nlost {} ({:.1}%)", s.lost, s.lost_pct));
+        }
+        self.stats_label.set_text(&text);
     }
 }
 
@@ -206,6 +236,13 @@ pub fn new(args: StreamPageArgs) -> StreamPage {
     let w = build_widgets(&window, &title, chromeless, pad_connected);
     w.stats_label.set_visible(show_stats);
 
+    // OSD line-1 facts, fixed for the session (the mode is negotiated per-session).
+    let mode = connector.mode();
+    let mode_line = format!("{}×{}@{}", mode.width, mode.height, mode.refresh_hz);
+    // Offset 0 = the host didn't answer the skew handshake / same host — flagged on the
+    // end-to-end line so an uncorrected cross-machine number is never shown silently.
+    let same_host = clock_offset_ns == 0;
+
     let capture = Rc::new(Capture {
         connector,
         window: window.clone(),
@@ -218,13 +255,13 @@ pub fn new(args: StreamPageArgs) -> StreamPage {
         held_buttons: RefCell::new(HashSet::new()),
     });
 
-    let present_ms = Rc::new(Cell::new(0.0f32));
+    let presented = Rc::new(PresentedStats::default());
     let hdr = Rc::new(Cell::new(false));
     spawn_frame_consumer(
         &w.picture,
         frames,
         clock_offset_ns,
-        present_ms.clone(),
+        presented.clone(),
         hdr.clone(),
     );
     attach_keyboard(&w.overlay, &window, &capture, &stop, &w.stats_label);
@@ -248,8 +285,10 @@ pub fn new(args: StreamPageArgs) -> StreamPage {
     StreamPage {
         page: w.page,
         stats_label: w.stats_label,
-        present_ms,
+        presented,
         hdr,
+        same_host,
+        mode_line,
     }
 }
 
@@ -456,12 +495,13 @@ fn attach_edge_reveal(
 /// then draws whatever paintable is current on its own frame clock. Ends itself when the
 /// channel closes or the picture is gone.
 ///
-/// Also the capture→present-ish measurement point: at each paintable set the frame's
-/// host capture pts is compared against the local wall clock expressed in the host clock
-/// (`clock_offset_ns`, same math as the session's decode latency). This is
-/// capture→paintable-SET — GTK's own present adds one compositor cycle after this. The
-/// 1 s p50 lands on the stats OSD (via `present_ms`) and in a "present window" debug
-/// line for headless validation.
+/// Also the `displayed` measurement point (design/stats-unification.md): each paintable
+/// set stamps the local wall clock, yielding end-to-end = capture→displayed (host-clock
+/// corrected via `clock_offset_ns`, p50+p95, measured directly) and the client-local
+/// `display` stage = decoded→displayed. This is capture→paintable-SET — GTK's own
+/// present adds one compositor cycle after this. The 1 s window results land on the
+/// stats OSD (via `PresentedStats`) and in a "present window" debug line for headless
+/// validation.
 /// One-entry cache of `ColorDesc` → `GdkColorState` (signaling changes at most on an
 /// SDR↔HDR flip, never per frame).
 #[derive(Default)]
@@ -516,7 +556,7 @@ fn spawn_frame_consumer(
     picture: &gtk::Picture,
     frames: async_channel::Receiver<DecodedFrame>,
     clock_offset_ns: i64,
-    present_ms: Rc<Cell<f32>>,
+    presented_stats: Rc<PresentedStats>,
     hdr: Rc<Cell<bool>>,
 ) {
     let picture = picture.downgrade();
@@ -528,7 +568,10 @@ fn spawn_frame_consumer(
     let mut yuv_state = ColorStateCache::default();
     let mut rgb_state = ColorStateCache::default();
     glib::spawn_future_local(async move {
-        let mut win_lat_us: Vec<u64> = Vec::with_capacity(256);
+        // Window samples (µs): end-to-end capture→displayed (host-clock corrected) and
+        // the client-local display stage decoded→displayed.
+        let mut win_e2e_us: Vec<u64> = Vec::with_capacity(256);
+        let mut win_disp_us: Vec<u64> = Vec::with_capacity(256);
         let mut win_start = Instant::now();
         while let Ok(f) = frames.recv().await {
             let Some(picture) = picture.upgrade() else {
@@ -601,26 +644,34 @@ fn spawn_frame_consumer(
                     }
                 }
             }
-            // Capture→paintable-set latency, host-clock corrected (same math and sanity
-            // bound as the session's decode-latency window).
+            // The `displayed` stamp: end-to-end = capture→displayed host-clock corrected
+            // (same clamp as the session's stage windows); display = decoded→displayed,
+            // single clock, no skew.
             if presented {
-                let lat = (crate::session::now_ns() as i128 + clock_offset_ns as i128
-                    - f.pts_ns as i128)
-                    .max(0) as u64;
-                if lat > 0 && lat < 10_000_000_000 {
-                    win_lat_us.push(lat / 1000);
+                let displayed_ns = crate::session::now_ns();
+                let e2e = (displayed_ns as i128 + clock_offset_ns as i128 - f.pts_ns as i128).max(0)
+                    as u64;
+                if e2e > 0 && e2e < 10_000_000_000 {
+                    win_e2e_us.push(e2e / 1000);
                 }
+                win_disp_us.push(displayed_ns.saturating_sub(f.decoded_ns) / 1000);
             }
             if win_start.elapsed() >= Duration::from_secs(1) {
-                win_lat_us.sort_unstable();
-                let p50 = win_lat_us.get(win_lat_us.len() / 2).copied().unwrap_or(0);
+                let frames = win_e2e_us.len();
+                let (e2e_p50, e2e_p95) = crate::session::window_percentiles(&mut win_e2e_us);
+                let (disp_p50, _) = crate::session::window_percentiles(&mut win_disp_us);
                 tracing::debug!(
-                    frames = win_lat_us.len(),
-                    present_p50_us = p50,
+                    frames,
+                    e2e_p50_us = e2e_p50,
+                    e2e_p95_us = e2e_p95,
+                    display_p50_us = disp_p50,
                     "present window"
                 );
-                present_ms.set(p50 as f32 / 1000.0);
-                win_lat_us.clear();
+                presented_stats.e2e_p50_ms.set(e2e_p50 as f32 / 1000.0);
+                presented_stats.e2e_p95_ms.set(e2e_p95 as f32 / 1000.0);
+                presented_stats.display_ms.set(disp_p50 as f32 / 1000.0);
+                win_e2e_us.clear();
+                win_disp_us.clear();
                 win_start = Instant::now();
             }
         }

clients/linux/src/video.rs

@@ -24,11 +24,15 @@ use std::os::fd::RawFd;
 use std::ptr;
 
 /// One decoded frame headed for the presenter, carrying the host capture timestamp so the
-/// UI can measure capture→paintable-set latency at the moment it presents.
+/// UI can measure capture→displayed latency at the moment it presents.
 pub struct DecodedFrame {
     /// Host-clock capture pts (ns) of the AU this image decoded from — compare against
     /// the local wall clock + `clock_offset_ns` at paintable-set time.
     pub pts_ns: u64,
+    /// Local wall clock (ns) when the decoder emitted this image — the `decoded`
+    /// measurement point (design/stats-unification.md); the presenter subtracts it from
+    /// its paintable-set stamp for the client-local `display` stage.
+    pub decoded_ns: u64,
     pub image: DecodedImage,
 }
 

clients/probe/README.md

@@ -14,7 +14,7 @@ example of driving the protocol end to end: QUIC control plane, UDP data plane,
 
 - **Receives a real stream**, writes a playable elementary stream (`.h265`/`.h264`/`.av1` — the
   extension tracks the **negotiated codec**; the probe advertises all three and the host picks), and
-  reports per-frame **capture→…→reassembled latency** percentiles (the host stamps each frame with
+  reports per-frame **capture→received latency** percentiles (the host stamps each frame with
   its capture clock).
 - **Verification mode** against a synthetic host — byte-checks deterministic test frames.
 - **Exercises every plane** with scripted test traffic:

clients/probe/src/main.rs

@@ -4,7 +4,7 @@
 //! * **verification** (`frames > 0`, synthetic host): byte-checks deterministic test frames;
 //! * **stream** (`frames == 0`, virtual host): receives real encoded AUs, writes a playable
 //!   elementary stream (the dump extension follows the negotiated codec — `.h265`/`.h264`/`.av1`;
-//!   the probe advertises all three), and reports per-frame **capture→…→reassembled latency**
+//!   the probe advertises all three), and reports per-frame **capture→received latency**
 //!   percentiles (the host stamps each frame with its capture wall clock; same-host runs share
 //!   that clock).
 //!
@@ -481,7 +481,7 @@ async fn session(args: Args) -> Result<()> {
     .await?;
 
     // Wall-clock skew handshake on the still-private control stream (before --remode/--speed-test
-    // take it): align our clock to the host's so the per-frame capture→reassembled latency is valid
+    // take it): align our clock to the host's so the per-frame capture→received latency is valid
     // across machines. `None` ⇒ an old host that doesn't answer — fall back to a shared clock (0).
     let clock_offset_ns = match punktfunk_core::quic::clock_sync(&mut send, &mut recv).await {
         Some(skew) => {
@@ -1051,7 +1051,7 @@ async fn session(args: Args) -> Result<()> {
                         continue;
                     }
                     bytes += frame.data.len() as u64;
-                    // capture→reassembled: our receive instant in the host clock (now + offset)
+                    // capture→received: our receive instant in the host clock (now + offset)
                     // minus the host's capture pts. offset is 0 same-host / old host.
                     let lat = (now_ns() as i128 + clock_offset as i128 - frame.pts_ns as i128)
                         .max(0) as u64;
@@ -1100,7 +1100,7 @@ async fn session(args: Args) -> Result<()> {
             lat_p99_us = pct(0.99),
             lat_max_us = latencies_us.last().copied().unwrap_or(0),
             skew_corrected,
-            "punktfunk/1 stream complete (capture→reassembled latency; skew_corrected=true ⇒ \
+            "punktfunk/1 stream complete (capture→received latency; skew_corrected=true ⇒ \
              cross-machine valid, false ⇒ same-host clock)"
         );
         if expected > 0 {

clients/windows/src/app/stream.rs

@@ -2,7 +2,7 @@
 //! the UI thread, then handed — presenter and all — to the dedicated render thread
 //! ([`crate::render`]), which presents decoded frames at stream cadence. The page itself only
 //! forwards panel size/DPI changes and draws the status-chip HUD overlay (mode · decode path ·
-//! HDR · fps/throughput/latency · capture hint).
+//! HDR · fps/goodput · end-to-end latency + stage equation · capture hint).
 
 use super::style::{edges, uniform};
 use super::Svc;
@@ -22,8 +22,9 @@ use windows_reactor::*;
 pub(crate) struct HudSample {
     pub(crate) stats: Stats,
     pub(crate) captured: bool,
-    /// `(presents/s, skipped/s, capture→presented p50 ms)` — see [`crate::render::present_stats`].
-    pub(crate) present: (u32, u32, f32),
+    /// The render thread's glass-side window (presents/s, skips, end-to-end p50/p95, display
+    /// stage p50) — see [`crate::render::present_stats`].
+    pub(crate) present: crate::render::PresentStats,
 }
 
 /// Props for the stream page: the services plus the live HUD sample that drives the overlay
@@ -171,13 +172,15 @@ fn fmt_uptime(secs: u32) -> String {
     }
 }
 
-/// The streaming HUD overlay (top-right), mirroring the Apple client: a chip row (mode · codec ·
-/// decode path · HDR), a stream line (decode fps / bitrate / decode time), a glass line (display
-/// presents + end-to-end latency decoded vs on-glass), a session line (host · time · loss), and
-/// the shortcut hints. Layered over the `SwapChainPanel` in the same grid cell.
+/// The streaming HUD overlay (top-right), unified stats vocabulary (design/stats-unification.md):
+/// a chip row (mode · codec · decode path · HDR), a stream line (received fps · goodput ·
+/// presenter fps), the end-to-end headline (capture→on-glass p50/p95, host-clock corrected), the
+/// stage equation (= host+network + decode + display, stage p50s), a session line
+/// (host · time · loss/skips), and the shortcut hints. Layered over the `SwapChainPanel` in the
+/// same grid cell.
 fn hud_overlay(hud: &HudSample, mode: Option<Mode>, host: &str) -> Element {
     let stats = &hud.stats;
-    let (pfps, skipped, glass_ms) = hud.present;
+    let present = &hud.present;
     let res = mode
         .map(|m| format!("{}\u{00D7}{}@{}", m.width, m.height, m.refresh_hz))
         .unwrap_or_else(|| "\u{2014}".into());
@@ -193,25 +196,38 @@ fn hud_overlay(hud: &HudSample, mode: Option<Mode>, host: &str) -> Element {
     if stats.hdr {
         chips.push(hud_chip("HDR", Color::rgb(255, 205, 90)).into());
     }
+    // Received fps + goodput, plus the presenter's own rate (Moonlight's "Rendering frame rate"
+    // analog — how often the display actually gets a new frame).
     let stream_line = format!(
-        "{:.0} fps \u{00B7} {:.1} Mb/s \u{00B7} decode {:.1} ms",
-        stats.fps, stats.mbps, stats.decode_ms
+        "{:.0} fps \u{00B7} {:.1} Mb/s \u{00B7} display {} fps",
+        stats.fps, stats.mbps, present.fps
     );
-    // End-to-end latency (host-clock corrected): capture→decoded from the pump, capture→on-glass
-    // from the render thread's post-Present stamp. `skipped` = newest-wins drops (expected when
-    // the stream outpaces the display); `lost` = unrecoverable network drops.
-    let glass_line = format!(
-        "display {pfps} fps \u{00B7} latency {:.1} ms decoded / {glass_ms:.1} ms on-glass",
-        stats.latency_ms
+    // The headline: end-to-end capture→displayed, measured directly post-Present (never the sum
+    // of the stage percentiles). `(same-host clock)` flags an uncorrected clock (offset == 0:
+    // same host, or the host skipped the skew handshake).
+    let mut e2e_line = format!(
+        "end-to-end {:.1} ms p50 \u{00B7} {:.1} p95 \u{00B7} capture\u{2192}on-glass",
+        present.e2e_p50_ms, present.e2e_p95_ms
+    );
+    if stats.same_host {
+        e2e_line.push_str(" (same-host clock)");
+    }
+    // The equation: the three stages tile the headline interval per frame; the window p50s only
+    // approximately sum (percentiles aren't additive).
+    let stage_line = format!(
+        "= host+network {:.1} + decode {:.1} + display {:.1}",
+        stats.hostnet_ms, stats.decode_ms, present.display_p50_ms
     );
     let mut session_bits: Vec<String> = Vec::new();
     if !host.is_empty() {
         session_bits.push(host.to_string());
     }
+    // `lost` = unrecoverable network drops (session-cumulative); `skipped` = the render thread's
+    // newest-wins drops last window (expected when the stream outpaces the display).
     session_bits.push(fmt_uptime(stats.uptime_secs));
     session_bits.push(format!("{} lost", stats.dropped));
-    if skipped > 0 {
-        session_bits.push(format!("{skipped} skipped"));
+    if present.skipped > 0 {
+        session_bits.push(format!("{} skipped", present.skipped));
     }
     let session_line = session_bits.join(" \u{00B7} ");
     let hint = if hud.captured {
@@ -228,7 +244,8 @@ fn hud_overlay(hud: &HudSample, mode: Option<Mode>, host: &str) -> Element {
         vstack((
             hstack(chips).spacing(6.0),
             dim(&stream_line),
-            dim(&glass_line),
+            dim(&e2e_line),
+            dim(&stage_line),
             dim(&session_line),
             text_block(hint)
                 .font_size(11.0)

clients/windows/src/main.rs

@@ -241,8 +241,8 @@ fn run_headless_cli(args: &[String], identity: (String, String)) {
                 session::SessionEvent::Stats(s) => tracing::info!(
                     fps = format!("{:.0}", s.fps),
                     mbps = format!("{:.1}", s.mbps),
-                    decode_ms = format!("{:.2}", s.decode_ms),
-                    lat_ms = format!("{:.2}", s.latency_ms),
+                    decode_p50_ms = format!("{:.2}", s.decode_ms),
+                    hostnet_p50_ms = format!("{:.2}", s.hostnet_ms),
                     frames_seen,
                     "stats"
                 ),

clients/windows/src/render.rs

@@ -10,27 +10,46 @@
 //! draw (and redraws the held frame after a resize — fresh back buffers are blank).
 
 use crate::present::Presenter;
-use crate::session::FrameRx;
+use crate::session::{FrameRx, FrameTimes};
 use crossbeam_channel::RecvTimeoutError;
 use std::sync::atomic::{AtomicBool, AtomicU32, AtomicU64, Ordering};
 use std::sync::Arc;
 use std::time::{Duration, Instant};
 
 /// The last 1-second render window, published for the HUD (one render thread at a time):
-/// presents/s, frames skipped by the newest-wins drain, and the capture→presented p50 in µs.
+/// presents/s, frames skipped by the newest-wins drain, the end-to-end (capture→on-glass)
+/// p50/p95 and the `display` stage (decoded→displayed) p50, all stamped post-`Present()`, in µs.
 /// Zeroed when a render thread starts so a new session never shows the previous one's numbers.
 static PRESENT_FPS: AtomicU32 = AtomicU32::new(0);
 static PRESENT_SKIPPED: AtomicU32 = AtomicU32::new(0);
-static PRESENT_P50_US: AtomicU64 = AtomicU64::new(0);
+static E2E_P50_US: AtomicU64 = AtomicU64::new(0);
+static E2E_P95_US: AtomicU64 = AtomicU64::new(0);
+static DISPLAY_P50_US: AtomicU64 = AtomicU64::new(0);
 
-/// `(presents/s, skipped/s, capture→presented p50 ms)` of the last render window — the HUD's
-/// display-side line.
-pub fn present_stats() -> (u32, u32, f32) {
-    (
-        PRESENT_FPS.load(Ordering::Relaxed),
-        PRESENT_SKIPPED.load(Ordering::Relaxed),
-        PRESENT_P50_US.load(Ordering::Relaxed) as f32 / 1000.0,
-    )
+/// The last render window's glass-side numbers (see the statics above) — the HUD's headline
+/// (end-to-end) and trailing stage (display) come from here.
+#[derive(Clone, Copy, Default, PartialEq)]
+pub struct PresentStats {
+    /// Presents per second (includes resize redraws of a held frame).
+    pub fps: u32,
+    /// Frames dropped by the newest-wins drain this window (client-side pacing skips).
+    pub skipped: u32,
+    /// End-to-end capture→displayed p50, ms (host-clock corrected, measured directly).
+    pub e2e_p50_ms: f32,
+    /// End-to-end capture→displayed p95, ms.
+    pub e2e_p95_ms: f32,
+    /// `display` stage p50, ms: decoded → displayed, single-clock client-local.
+    pub display_p50_ms: f32,
+}
+
+pub fn present_stats() -> PresentStats {
+    PresentStats {
+        fps: PRESENT_FPS.load(Ordering::Relaxed),
+        skipped: PRESENT_SKIPPED.load(Ordering::Relaxed),
+        e2e_p50_ms: E2E_P50_US.load(Ordering::Relaxed) as f32 / 1000.0,
+        e2e_p95_ms: E2E_P95_US.load(Ordering::Relaxed) as f32 / 1000.0,
+        display_p50_ms: DISPLAY_P50_US.load(Ordering::Relaxed) as f32 / 1000.0,
+    }
 }
 
 /// UI-thread → render-thread state. Size is packed into ONE atomic (w<<32|h) so a resize never
@@ -101,8 +120,9 @@ impl Drop for RenderThread {
 struct SendPresenter(Presenter);
 unsafe impl Send for SendPresenter {}
 
-/// Spawn the render thread. `frames` carries `(frame, capture pts_ns)`; `clock_offset_ns` maps our
-/// wall clock onto the host's so the logged present latency is end-to-end (same math as the pump).
+/// Spawn the render thread. `frames` carries `(frame, FrameTimes)`; `clock_offset_ns` maps our
+/// wall clock onto the host's so the end-to-end (capture→on-glass) number is cross-machine valid
+/// (same math as the pump's host+network stage).
 pub fn spawn(
     presenter: Presenter,
     frames: FrameRx,
@@ -147,12 +167,17 @@ fn run(presenter: SendPresenter, frames: FrameRx, shared: Arc<RenderShared>, clo
     let mut applied = (0u32, 0u32, 0u32); // last (w, h, dpi) handed to the presenter
     let mut presented = 0u32;
     let mut dropped = 0u32;
-    let mut lat_us: Vec<u64> = Vec::with_capacity(256);
+    // 1 s tumbling windows: end-to-end (capture→displayed) and the display stage
+    // (decoded→displayed), sampled post-Present. Percentiles only (spec: stats-unification.md).
+    let mut e2e_us: Vec<u64> = Vec::with_capacity(256);
+    let mut display_us: Vec<u64> = Vec::with_capacity(256);
     let mut window_start = Instant::now();
     let mut last_dpi_poll = Instant::now();
     PRESENT_FPS.store(0, Ordering::Relaxed);
     PRESENT_SKIPPED.store(0, Ordering::Relaxed);
-    PRESENT_P50_US.store(0, Ordering::Relaxed);
+    E2E_P50_US.store(0, Ordering::Relaxed);
+    E2E_P95_US.store(0, Ordering::Relaxed);
+    DISPLAY_P50_US.store(0, Ordering::Relaxed);
 
     loop {
         if shared.stop.load(Ordering::SeqCst) {
@@ -198,29 +223,55 @@ fn run(presenter: SendPresenter, frames: FrameRx, shared: Arc<RenderShared>, clo
             p.set_hdr_metadata(meta);
         }
 
-        let pts_ns = newest.as_ref().map(|(_, pts)| *pts);
+        let times: Option<FrameTimes> = newest.as_ref().map(|(_, t)| *t);
         p.present(newest.map(|(f, _)| f));
         presented += 1;
-        if let Some(pts) = pts_ns {
-            // Capture→presented, host-clock corrected — the glass-side companion to the pump's
-            // capture→decoded p50.
-            let lat = (now_ns() as i128 + clock_offset_ns as i128 - pts as i128).max(0) as u64;
-            if lat > 0 && lat < 10_000_000_000 {
-                lat_us.push(lat / 1000);
+        if let Some(t) = times {
+            // The `displayed` point: post-Present() on this thread (the honest best-effort
+            // presentation instant on Windows — endpoint label `capture→on-glass`).
+            let displayed_ns = now_ns();
+            // End-to-end = capture → displayed, host-clock corrected, measured directly
+            // (never the sum of stage percentiles). Clamped (0, 10 s).
+            let e2e =
+                (displayed_ns as i128 + clock_offset_ns as i128 - t.pts_ns as i128).max(0) as u64;
+            if e2e > 0 && e2e < 10_000_000_000 {
+                e2e_us.push(e2e / 1000);
+            }
+            // `display` stage = decoded → displayed, single-clock client-local.
+            let disp = displayed_ns.saturating_sub(t.decoded_ns);
+            if disp < 10_000_000_000 {
+                display_us.push(disp / 1000);
             }
         }
 
         if window_start.elapsed() >= Duration::from_secs(1) {
-            lat_us.sort_unstable();
-            let p50 = lat_us.get(lat_us.len() / 2).copied().unwrap_or(0);
-            tracing::debug!(presented, dropped, present_p50_us = p50, "render window");
+            e2e_us.sort_unstable();
+            display_us.sort_unstable();
+            let p50 = |v: &[u64]| v.get(v.len() / 2).copied().unwrap_or(0);
+            // p95 = sorted[min(len*95/100, len-1)] — the empty-window case falls to 0 via `get`.
+            let p95 = |v: &[u64]| {
+                v.get((v.len() * 95 / 100).min(v.len().saturating_sub(1)))
+                    .copied()
+                    .unwrap_or(0)
+            };
+            tracing::debug!(
+                presented,
+                dropped,
+                e2e_p50_us = p50(&e2e_us),
+                e2e_p95_us = p95(&e2e_us),
+                display_p50_us = p50(&display_us),
+                "render window"
+            );
             PRESENT_FPS.store(presented, Ordering::Relaxed);
             PRESENT_SKIPPED.store(dropped, Ordering::Relaxed);
-            PRESENT_P50_US.store(p50, Ordering::Relaxed);
+            E2E_P50_US.store(p50(&e2e_us), Ordering::Relaxed);
+            E2E_P95_US.store(p95(&e2e_us), Ordering::Relaxed);
+            DISPLAY_P50_US.store(p50(&display_us), Ordering::Relaxed);
             window_start = Instant::now();
             presented = 0;
             dropped = 0;
-            lat_us.clear();
+            e2e_us.clear();
+            display_us.clear();
         }
     }
     tracing::info!("render thread exiting");

clients/windows/src/session.rs

@@ -46,11 +46,18 @@ pub struct SessionParams {
 
 #[derive(Clone, Copy, Default, PartialEq)]
 pub struct Stats {
+    /// AUs received (reassembled) per second — actual-elapsed-time denominator.
     pub fps: f32,
+    /// Received payload goodput (excludes FEC overhead).
     pub mbps: f32,
+    /// `decode` stage p50 over the last 1 s window: received → decoded, client-local clock.
     pub decode_ms: f32,
-    /// Median capture→decoded latency over the last window (host-clock corrected).
-    pub latency_ms: f32,
+    /// `host+network` stage p50 over the last 1 s window: capture (`pts_ns`) → received,
+    /// host-clock corrected via `clock_offset_ns`.
+    pub hostnet_ms: f32,
+    /// True when `clock_offset_ns == 0` (host didn't answer the skew handshake / same host) —
+    /// the HUD appends `(same-host clock)` to the end-to-end line.
+    pub same_host: bool,
     /// True when decoding on the GPU (D3D11VA) vs. CPU (software).
     pub hardware: bool,
     /// True when the stream is BT.2020 PQ HDR10 (last decoded frame).
@@ -81,9 +88,19 @@ pub enum SessionEvent {
     Stats(Stats),
 }
 
-/// Decoded frames + their host-capture `pts_ns`, session pump → render thread (crossbeam so that
+/// Per-frame measurement points carried with a decoded frame to the render thread: the host
+/// capture clock (`pts_ns`) and our local `decoded` stamp (wall-clock ns). Post-`Present()` the
+/// render thread derives the `display` stage (displayed − decoded, single-clock) and the
+/// end-to-end headline (displayed + clock_offset − pts) from them.
+#[derive(Clone, Copy)]
+pub struct FrameTimes {
+    pub pts_ns: u64,
+    pub decoded_ns: u64,
+}
+
+/// Decoded frames + their measurement points, session pump → render thread (crossbeam so that
 /// thread can block with a timeout — async-channel has no `recv_timeout`).
-pub type FrameRx = crossbeam_channel::Receiver<(DecodedFrame, u64)>;
+pub type FrameRx = crossbeam_channel::Receiver<(DecodedFrame, FrameTimes)>;
 
 pub struct SessionHandle {
     pub events: async_channel::Receiver<SessionEvent>,
@@ -205,7 +222,7 @@ impl AudioDec {
 fn pump(
     params: SessionParams,
     ev_tx: async_channel::Sender<SessionEvent>,
-    frame_tx: crossbeam_channel::Sender<(DecodedFrame, u64)>,
+    frame_tx: crossbeam_channel::Sender<(DecodedFrame, FrameTimes)>,
     frame_rx: FrameRx,
     stop: Arc<AtomicBool>,
 ) {
@@ -310,8 +327,9 @@ fn pump(
     let mut window_start = Instant::now();
     let mut frames_n = 0u32;
     let mut bytes_n = 0u64;
-    let mut decode_us_sum = 0u64;
-    let mut lat_us: Vec<u64> = Vec::with_capacity(256);
+    // 1 s tumbling stage windows (spec: design/stats-unification.md — percentiles, never means).
+    let mut hostnet_us: Vec<u64> = Vec::with_capacity(256);
+    let mut decode_us: Vec<u64> = Vec::with_capacity(256);
     let mut pcm = vec![0f32; 5760 * channels as usize]; // scratch: max Opus frame (120 ms) × channels
                                                         // Loss recovery: watch the host→client unrecoverable-drop count and ask for an IDR when it climbs.
     let mut last_dropped = connector.frames_dropped();
@@ -323,7 +341,18 @@ fn pump(
         }
         match connector.next_frame(Duration::from_millis(4)) {
             Ok(frame) => {
-                let t0 = Instant::now();
+                // The `received` point: AU fully reassembled, handed to us, before decode.
+                let received_ns = now_ns();
+                // fps = AUs received per second, Mb/s = received goodput (spec: counted at the
+                // received point, not the decoded one).
+                frames_n += 1;
+                bytes_n += frame.data.len() as u64;
+                // `host+network` stage: capture → received, host-clock corrected. Clamped (0, 10 s).
+                let hostnet = (received_ns as i128 + clock_offset as i128 - frame.pts_ns as i128)
+                    .max(0) as u64;
+                if hostnet > 0 && hostnet < 10_000_000_000 {
+                    hostnet_us.push(hostnet / 1000);
+                }
                 // A D3D11VA→software demotion (see `Decoder::decode`) starts a FRESH decoder that
                 // has none of the stream's parameter sets; under infinite GOP it would sit on
                 // "PPS id out of range" forever. Detect the transition and force a new IDR so the
@@ -336,6 +365,8 @@ fn pump(
                 }
                 match decoded {
                     Ok(Some(decoded)) => {
+                        // The `decoded` point: decoder output frame available.
+                        let decoded_ns = now_ns();
                         total_frames += 1;
                         hdr = decoded.hdr();
                         // The backend can demote D3D11VA → software mid-session on a hardware error.
@@ -350,19 +381,17 @@ fn pump(
                                 "first frame decoded"
                             );
                         }
-                        // Latency: our wall clock expressed in the host's capture clock,
-                        // minus the host-stamped capture pts (same math as client-rs).
-                        let lat = (now_ns() as i128 + clock_offset as i128 - frame.pts_ns as i128)
-                            .max(0) as u64;
-                        if lat > 0 && lat < 10_000_000_000 {
-                            lat_us.push(lat / 1000);
-                        }
-                        decode_us_sum += t0.elapsed().as_micros() as u64;
-                        frames_n += 1;
-                        bytes_n += frame.data.len() as u64;
+                        // `decode` stage: received → decoded, single-clock client-local.
+                        decode_us.push(decoded_ns.saturating_sub(received_ns) / 1000);
                         // Newest wins: displace the oldest queued frame when the renderer lags.
                         if let Err(crossbeam_channel::TrySendError::Full(item)) =
-                            frame_tx.try_send((decoded, frame.pts_ns))
+                            frame_tx.try_send((
+                                decoded,
+                                FrameTimes {
+                                    pts_ns: frame.pts_ns,
+                                    decoded_ns,
+                                },
+                            ))
                         {
                             let _ = frame_rx.try_recv();
                             let _ = frame_tx.try_send(item);
@@ -413,23 +442,23 @@ fn pump(
 
         if window_start.elapsed() >= Duration::from_secs(1) {
             let secs = window_start.elapsed().as_secs_f32();
-            lat_us.sort_unstable();
-            let p50 = lat_us.get(lat_us.len() / 2).copied().unwrap_or(0);
+            hostnet_us.sort_unstable();
+            decode_us.sort_unstable();
+            let p50 = |v: &[u64]| v.get(v.len() / 2).copied().unwrap_or(0);
+            let (hostnet_p50, decode_p50) = (p50(&hostnet_us), p50(&decode_us));
             tracing::debug!(
                 fps = frames_n,
-                lat_p50_us = p50,
+                hostnet_p50_us = hostnet_p50,
+                decode_p50_us = decode_p50,
                 total_frames,
                 "stream window"
             );
             let _ = ev_tx.try_send(SessionEvent::Stats(Stats {
                 fps: frames_n as f32 / secs,
                 mbps: bytes_n as f32 * 8.0 / 1e6 / secs,
-                decode_ms: if frames_n > 0 {
-                    decode_us_sum as f32 / frames_n as f32 / 1000.0
-                } else {
-                    0.0
-                },
-                latency_ms: p50 as f32 / 1000.0,
+                decode_ms: decode_p50 as f32 / 1000.0,
+                hostnet_ms: hostnet_p50 as f32 / 1000.0,
+                same_host: clock_offset == 0,
                 hardware,
                 hdr,
                 codec: connector.codec,
@@ -439,8 +468,8 @@ fn pump(
             window_start = Instant::now();
             frames_n = 0;
             bytes_n = 0;
-            decode_us_sum = 0;
-            lat_us.clear();
+            hostnet_us.clear();
+            decode_us.clear();
         }
     };