perf(latency): tier-0 attribution + tier-1 send-path levers from the latency plan

design/latency-reduction-2026-07.md T0.1/T0.2/T1.2/T1.3:

- T1.2 rate-capped front-loaded pacing: the paced overflow's budget is now
  min(0.9x slack, overflow wire time at ~3x the live encoder bitrate)
  (PUNKTFUNK_PACE_FACTOR, 0 = legacy deadline-only spread). A 300 KB-1 MB
  frame's tail leaves in ~2-5 ms instead of smearing across ~15 ms at 60 fps;
  GameStream schedule byte-identical (pins unchanged).
- T1.3 data-first wire order: packetize emits every block's data shards before
  any parity (per-block parity pools keep all blocks' parity alive for the
  second pass), so lossless completion stops waiting behind the parity tail.
  EOF = last emitted packet; receiver already order-agnostic.
- T0.1 staged 0xCF: HostTiming gains an append-extensible per-stage tail
  (queue/encode/pace us; seal+channel-wait derived as residual) - no cap bit
  needed, old peers read the 13-byte prefix. Joined client-side into
  Stats::host_{queue,encode,xfer,pace}_ms, the OSD detailed tier, and the
  probe's report.
- T0.2 true on-glass present timing: VK_KHR_present_id/present_wait enabled
  when supported; a PresentTimer waiter thread resolves each present id to
  real visibility, replacing the submit-time display stamp (which undercounts
  by up to a refresh and hides a silent-FIFO standing queue).

Validated on .21: core 185 + host 185 tests, pf-presenter 19, clippy
-D warnings across all five touched crates; loss-harness recovery curve
unchanged; C ABI harness round-trips.

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

crates/pf-presenter/src/vk/present.rs

@@ -569,20 +569,32 @@ impl Presenter {
             let swapchains = [self.swapchain];
             let indices = [index];
             let present_sems = [render_sem];
+            // On-glass timing (T0.2): attach a monotonically increasing present id the
+            // PresentTimer's `vkWaitForPresentKHR` resolves to real visibility.
+            let ids = [self.next_present_id + 1];
+            let mut pid_info = vk::PresentIdKHR::default().present_ids(&ids);
+            let mut present_info = vk::PresentInfoKHR::default()
+                .wait_semaphores(&present_sems)
+                .swapchains(&swapchains)
+                .image_indices(&indices);
+            if self.present_timer.is_some() {
+                self.next_present_id += 1;
+                present_info = present_info.push_next(&mut pid_info);
+            }
             // Same queue external-sync rule as the submit above. Scoped tightly: the
             // OUT_OF_DATE arm re-enters the lock via recreate_swapchain's queue drain.
             let present_res = {
                 let _q = self.queue_lock.guard();
-                self.swap_d.queue_present(
-                    self.queue,
-                    &vk::PresentInfoKHR::default()
-                        .wait_semaphores(&present_sems)
-                        .swapchains(&swapchains)
-                        .image_indices(&indices),
-                )
+                self.swap_d.queue_present(self.queue, &present_info)
             };
             match present_res {
-                Ok(_) => Ok(true),
+                Ok(_) => {
+                    // A failed present's id may never signal — claimable only on Ok.
+                    if self.present_timer.is_some() {
+                        self.last_presented = Some((self.swapchain, self.next_present_id));
+                    }
+                    Ok(true)
+                }
                 Err(vk::Result::ERROR_OUT_OF_DATE_KHR) => {
                     self.recreate_swapchain(window)?;
                     Ok(false)