feat(android): the decode stage answers where its time goes, HUD on or off

P3 decode science: every AU is stamped as its last piece enters the codec, so
the decode stage splits into feed (received→queued: hand-off + input-slot wait)
and codec (queued→decoded: the decoder alone — a slice head start would show
here). The split + an always-on capture→decoded e2e ride the 1 Hz pf-present
line, so a wireless HUD-off A/B reads everything from logcat; the HUD equation
gains the split (indices 30/31), the skipped counter tells benign newest-wins
pacing from parked-AU overflow (32), and a −2-refresh Apple-HUD-equivalent twin
makes iPhone comparisons honest (Apple shaves its OS floor; Android shows raw).

Connect now logs the per-mime decoder picks + FEATURE_PartialFrame verdicts
(tag pf.caps) — on the NP3 all three c2.qti low-latency decoders say no, so
parts delivery never arms and P2d is inert there; a debug.punktfunk.force_parts
sysprop overrides the probe for the on-glass question the API cannot answer.
Forced on glass: c2.qti accepts PARTIAL_FRAME pieces without erroring but only
assembles them — codec time unchanged, so the overlap is dead on SM8735 either
way.

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

clients/android/native/src/decode/async_loop.rs

@@ -16,7 +16,7 @@ use std::time::{Duration, Instant};
 use super::display::{
     apply_hdr_dataspace, install_render_callback, release_render_callback, DisplayTracker,
 };
-use super::latency::{note_decoded_pts, now_realtime_ns, take_flags};
+use super::latency::{note_decoded_pts, now_realtime_ns, take_flags, take_stamp};
 use super::presenter::{presenter_disabled_by_sysprop, PresentMeter, PresentPriority, Presenter};
 use super::setup::{
     android_hdr_static_info, boost_hot_threads, boost_thread_priority, codec_mime,
@@ -280,6 +280,10 @@ pub(super) fn run_async(
     let mut oversized_dropped: u64 = 0;
     // Slice-progressive continuity ledger (see `PartFeed`).
     let mut part_open: Option<PartFeed> = None;
+    // Queued-instant stamps (pts → realtime ns at the AU's LAST piece entering the codec) — the
+    // P3 decode-split ledger: `feed` = received→queued, `codec` = queued→decoded. Always on
+    // (one vDSO clock read per AU); consumed by `present_ready`.
+    let mut queued_stamps: VecDeque<(u64, i128)> = VecDeque::new();
     // Freeze-until-reanchor gate (see the sync loop for the rationale). Armed on a frame-index gap
     // (the feeder's Au verdict), a parked-AU overflow drop, a dropped-count climb, or a recoverable
     // codec error; `recovery_flags` carries each AU's user_flags from `dispatch_event` (feed) to
@@ -349,7 +353,7 @@ pub(super) fn run_async(
                 p.on_vsync();
             }
         }
-        stats.note_skipped(aus_dropped); // parked-AU overflow drops are client-side skips too
+        stats.note_skipped_overflow(aus_dropped); // parked-AU overflow: skips, flagged as such
         if fmt_dirty {
             apply_hdr_dataspace(&codec, &window, &mut applied_ds);
         }
@@ -361,6 +365,7 @@ pub(super) fn run_async(
             &mut fed,
             &mut oversized_dropped,
             &mut part_open,
+            &mut queued_stamps,
             &mut gate,
         );
         let had_output = !ready.is_empty();
@@ -372,6 +377,8 @@ pub(super) fn run_async(
             &mut ready,
             &stats,
             &in_flight,
+            &mut queued_stamps,
+            &meter,
             clock_offset.load(Ordering::Relaxed),
             &tracker,
             &mut presenter,
@@ -762,6 +769,7 @@ pub(super) struct PartFeed {
 /// [`BUFFER_FLAG_PARTIAL_FRAME`] except the AU's last, all at the AU's pts. `part_open` is the
 /// continuity ledger — any break (gap, orphan, oversize) abandons the AU per [`PartFeed::pts_us`]'s
 /// close contract and re-syncs at the next `first`.
+#[allow(clippy::too_many_arguments)] // one call site; the split ledger threads through like the gate
 fn feed_ready(
     codec: &MediaCodec,
     client: &NativeClient,
@@ -770,6 +778,7 @@ fn feed_ready(
     fed: &mut u64,
     oversized_dropped: &mut u64,
     part_open: &mut Option<PartFeed>,
+    queued_stamps: &mut VecDeque<(u64, i128)>,
     gate: &mut ReanchorGate,
 ) {
     while !pending_aus.is_empty() && !free_inputs.is_empty() {
@@ -859,9 +868,15 @@ fn feed_ready(
             }
         } else {
             // `fed` counts ACCESS UNITS toward the HUD's fed/decoded balance — the closing
-            // piece (or a whole AU) bumps it.
+            // piece (or a whole AU) bumps it. The queued stamp marks the same instant (the AU
+            // is fully in the codec's hands): the P3 decode split measures `codec` from here,
+            // so a slice-progressive head start shows up as codec-pure shrink.
             if last {
                 *fed += 1;
+                queued_stamps.push_back((pts_us, now_realtime_ns()));
+                if queued_stamps.len() > IN_FLIGHT_CAP {
+                    queued_stamps.pop_front(); // stale — codec never echoed it back
+                }
             }
             *part_open = if last {
                 None
@@ -876,7 +891,8 @@ fn feed_ready(
     }
 }
 
-/// Route the ready outputs toward glass. With the timeline presenter (default): fold each output
+/// Route the ready outputs toward glass, recording each one's decode-split + e2e first. With the
+/// timeline presenter (default): fold each output
 /// through the re-anchor gate in pts order, hand the approved ones to the presenter's store
 /// (newest-wins / smoothing FIFO — the actual release happens in `Presenter::pump`, budgeted and
 /// timeline-timed), and release withheld concealment unrendered. Legacy (`arrival` sysprop):
@@ -892,6 +908,8 @@ fn present_ready(
     ready: &mut Vec<OutputReady>,
     stats: &crate::stats::VideoStats,
     in_flight: &Mutex<VecDeque<(u64, i128)>>,
+    queued_stamps: &mut VecDeque<(u64, i128)>,
+    meter: &PresentMeter,
     clock_offset: i64,
     tracker: &DisplayTracker,
     presenter: &mut Option<Presenter>,
@@ -903,22 +921,42 @@ fn present_ready(
     if ready.is_empty() {
         return;
     }
-    // Pair each output's decode stage (feeds the ABR decode signal always; the HUD histogram only
-    // while visible) — both consume the receipt map, so enter for either.
-    if stats.enabled() || measure_decode {
+    // Pair each output's decode stage (the ABR decode signal + the HUD histogram consume the
+    // receipt map; the P3 split's codec-pure half needs only the queued stamp, so it records
+    // even with both off — that keeps the 1 Hz pf.present mirror HUD-off readable).
+    {
+        let want_stage = stats.enabled() || measure_decode;
         let mut g = in_flight
             .lock()
             .unwrap_or_else(std::sync::PoisonError::into_inner);
         for o in ready.iter() {
-            note_decoded_pts(
-                client,
-                measure_decode,
-                stats,
-                &mut g,
-                clock_offset,
-                o.pts_us,
-                o.decoded_ns,
-            );
+            let received_ns = if want_stage {
+                note_decoded_pts(
+                    client,
+                    measure_decode,
+                    stats,
+                    &mut g,
+                    clock_offset,
+                    o.pts_us,
+                    o.decoded_ns,
+                )
+            } else {
+                None
+            };
+            let queued = take_stamp(queued_stamps, o.pts_us);
+            let codec_us = queued.map(|q| ((o.decoded_ns - q).max(0) / 1000) as u64);
+            let feed_us = match (queued, received_ns) {
+                (Some(q), Some(r)) => Some(((q - r).max(0) / 1000) as u64),
+                _ => None,
+            };
+            // Always-on e2e for the 1 Hz pf.present mirror (same formula + clamp as the HUD's
+            // capture→decoded headline in `note_decoded_pts`).
+            let e2e_ns = o.decoded_ns + clock_offset as i128 - o.pts_us as i128 * 1000;
+            let e2e_us = (e2e_ns > 0 && e2e_ns < 10_000_000_000).then_some((e2e_ns / 1000) as u64);
+            meter.note_decode(feed_us, codec_us, e2e_us);
+            if let Some(c) = codec_us {
+                stats.note_decode_split(feed_us, c);
+            }
         }
     }
     // Fold EVERY output through the gate in pts (== decode) order — even the ones newest-wins discards —

clients/android/native/src/decode/latency.rs

@@ -20,7 +20,8 @@ pub(super) fn now_realtime_ns() -> i128 {
 /// entries older than it 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).
 /// `decoded_ns` is the availability instant: the dequeue (sync loop) or the output callback's
-/// stamp (async loop).
+/// stamp (async loop). Returns the receipt stamp it paired (if any) so the caller can split the
+/// `decode` stage further (feed wait vs codec-pure) without re-walking the map.
 pub(super) fn note_decoded_pts(
     client: &NativeClient,
     measure_decode: bool,
@@ -29,7 +30,7 @@ pub(super) fn note_decoded_pts(
     clock_offset: i64,
     pts_us: u64,
     decoded_ns: i128,
-) {
+) -> Option<i128> {
     // 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() {
@@ -61,6 +62,24 @@ pub(super) fn note_decoded_pts(
         let e2e_us = (e2e_ns > 0 && e2e_ns < 10_000_000_000).then_some((e2e_ns / 1000) as u64);
         stats.note_decoded(e2e_us, decode_us);
     }
+    received_ns
+}
+
+/// The queued-instant stamp for a decoded output, keyed by the echoed `presentationTimeUs` — the
+/// same monotonic evict-as-you-go pairing as [`take_flags`], over an `(pts_us, realtime_ns)` map
+/// (the feed side stamps each AU as its last piece enters the codec). A miss returns `None` —
+/// the split is simply not recorded for that frame.
+pub(super) fn take_stamp(map: &mut VecDeque<(u64, i128)>, pts_us: u64) -> Option<i128> {
+    while let Some(&(p, t)) = map.front() {
+        if p > pts_us {
+            break; // future frame — leave it for its own output buffer
+        }
+        map.pop_front();
+        if p == pts_us {
+            return Some(t);
+        }
+    }
+    None
 }
 
 /// The AU `user_flags` for a decoded output, keyed by the echoed `presentationTimeUs`. Recovery

clients/android/native/src/decode/presenter.rs

@@ -126,6 +126,15 @@ pub(super) struct PresentMeter {
 struct PresentMeterInner {
     latch_us: Vec<u64>,
     displays: u64,
+    /// The `decode` stage's feed split, received→queued µs (P3 science: hand-off + input-slot
+    /// wait). Empty when no receipt stamp matched (HUD off and ABR not measuring decode).
+    feed_us: Vec<u64>,
+    /// The codec-pure half, queued→decoded µs, measured from the AU's LAST piece — always on,
+    /// so a HUD-off logcat A/B still reads the decoder's own time.
+    codec_us: Vec<u64>,
+    /// Capture→decoded end-to-end µs (skew-corrected, clamped) — always on for the same reason:
+    /// the wireless A/B's headline without having to reach the on-screen HUD.
+    e2e_us: Vec<u64>,
 }
 
 impl PresentMeter {
@@ -134,6 +143,9 @@ impl PresentMeter {
             inner: Mutex::new(PresentMeterInner {
                 latch_us: Vec::with_capacity(256),
                 displays: 0,
+                feed_us: Vec::with_capacity(256),
+                codec_us: Vec::with_capacity(256),
+                e2e_us: Vec::with_capacity(256),
             }),
         }
     }
@@ -152,14 +164,51 @@ impl PresentMeter {
         }
     }
 
-    fn drain(&self) -> (Vec<u64>, u64) {
+    /// One decoded frame's always-on measurements: the `decode`-stage split (feed =
+    /// received→queued when a receipt stamp matched; codec = queued→decoded when the queued
+    /// stamp did) and the capture→decoded end-to-end, µs. Decode thread; poison-proof.
+    pub(super) fn note_decode(
+        &self,
+        feed_us: Option<u64>,
+        codec_us: Option<u64>,
+        e2e_us: Option<u64>,
+    ) {
+        let mut g = self
+            .inner
+            .lock()
+            .unwrap_or_else(std::sync::PoisonError::into_inner);
+        if let Some(f) = feed_us {
+            if g.feed_us.len() < 4096 {
+                g.feed_us.push(f);
+            }
+        }
+        if let Some(c) = codec_us {
+            if g.codec_us.len() < 4096 {
+                g.codec_us.push(c);
+            }
+        }
+        if let Some(e) = e2e_us {
+            if g.e2e_us.len() < 4096 {
+                g.e2e_us.push(e);
+            }
+        }
+    }
+
+    #[allow(clippy::type_complexity)] // one caller unpacks it in place; a struct would be noise
+    fn drain(&self) -> (Vec<u64>, u64, Vec<u64>, Vec<u64>, Vec<u64>) {
         let mut g = self
             .inner
             .lock()
             .unwrap_or_else(std::sync::PoisonError::into_inner);
         let displays = g.displays;
         g.displays = 0;
-        (std::mem::take(&mut g.latch_us), displays)
+        (
+            std::mem::take(&mut g.latch_us),
+            displays,
+            std::mem::take(&mut g.feed_us),
+            std::mem::take(&mut g.codec_us),
+            std::mem::take(&mut g.e2e_us),
+        )
     }
 }
 
@@ -386,7 +435,9 @@ impl Presenter {
     /// `released` (to glass) / `displays` (OnFrameRendered confirms) / `paced` (policy drops) /
     /// `noBudget` (waits on the closed budget) / `forced` (stale force-opens — 0 when healthy) /
     /// `qDry` (FIFO underflows) / `pace` (decoded→release) / `latch` (release→displayed) /
-    /// `vsync` (the measured panel period).
+    /// `feed`+`codec` (the decode stage split: received→queued hand-off/slot wait + the
+    /// codec-pure queued→decoded time) / `e2e` (capture→decoded, skew-corrected — the wireless
+    /// A/B headline) / `vsync` (the measured panel period).
     ///
     /// Returns this window's CIRCULAR latch statistics `(vector-mean latch ns mod panel period,
     /// coherence ‰)` when a window actually flushed — the phase-lock reporter's v2 error signal
@@ -400,11 +451,14 @@ impl Presenter {
             return None;
         }
         self.last_flush = Instant::now();
-        let (latch, displays) = meter.drain();
+        let (latch, displays, feed, codec, e2e) = meter.drain();
         if self.released == 0 && displays == 0 {
             return None; // idle stream — nothing worth a line
         }
         let (pace_p50, pace_max) = p50_max_ms(std::mem::take(&mut self.pace_us));
+        let (feed_p50, feed_max) = p50_max_ms(feed);
+        let (codec_p50, codec_max) = p50_max_ms(codec);
+        let (e2e_p50, e2e_max) = p50_max_ms(e2e);
         let circ = clock.and_then(|c| {
             punktfunk_core::phase::circular_latch(&latch, c.panel_period_ns().max(c.period_ns()))
         });
@@ -416,7 +470,9 @@ impl Presenter {
         log::info!(
             target: "pf.present",
             "released={} displays={} paced={} noBudget={} forced={} qDry={} \
-             paceMs p50={:.2} max={:.2} latchMs p50={:.2} max={:.2} circ={:.2}ms coh={} \
+             paceMs p50={:.2} max={:.2} latchMs p50={:.2} max={:.2} \
+             feedMs p50={:.2} max={:.2} codecMs p50={:.2} max={:.2} \
+             e2eMs p50={:.2} max={:.2} circ={:.2}ms coh={} \
              vsyncMs={:.2} panelMs={:.2}",
             self.released,
             displays,
@@ -428,6 +484,12 @@ impl Presenter {
             pace_max,
             latch_p50,
             latch_max,
+            feed_p50,
+            feed_max,
+            codec_p50,
+            codec_max,
+            e2e_p50,
+            e2e_max,
             circ.map(|(m, _)| m as f64 / 1e6).unwrap_or(0.0),
             circ.map(|(_, c)| c).unwrap_or(0),
             period_ms,