fix(encode): make LTR-RFI loss recovery sound under sustained loss

Field report (lid-closed Intel laptop, ~6-19% sustained loss): the stream
never healed — permanent macroblock soup. Three stacked bugs:

- QSV answered RFI with PreferredRefList only, a reorder HINT per the VPL
  spec — the recovery frame could keep predicting from tainted short-term
  refs. Now rejects every other DPB candidate (RejectedRefList) and caps
  L0 at one active entry (AVC/HEVC), matching AMF's hard
  ForceLTRReferenceBitfield / NVENC invalidation semantics.
- Neither QSV nor AMF taint-swept LTR slots across losses: a slot marked
  inside the client's corrupt window became the "known-good" anchor of the
  NEXT loss, propagating corruption through every recovery. Both now drop
  slots at-or-after the loss start before picking an anchor, and guard a
  queued force whose slot the sweep emptied (no false recovery_anchor tag).
- The native plane re-anchored the FULL IDR cooldown on every successful
  RFI, so under sustained loss the client's escalating keyframe requests
  were coalesced away indefinitely (field log: dozens swallowed, one IDR
  per ~8 s). RFI now anchors a 300 ms echo window with a 2-swallow budget
  per loss episode; a client still asking past that gets its IDR.

Live-validated on Arc (qsv feature): 6/6 including the new
qsv_live_ltr_rfi_taint_sweep_declines (a loss covering every live mark
declines the RFI and falls back to IDR recovery).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

crates/pf-encode/src/enc/windows/amf.rs

@@ -2077,9 +2077,15 @@ impl Encoder for AmfEncoder {
             }
             // Apply a queued force (from invalidate_ref_frames / the test hook) to THIS frame: it
             // becomes the clean re-anchor P-frame the client lifts its post-loss freeze on.
+            // Guard against a slot the taint sweep emptied since the force was queued: the
+            // HARDWARE slot still holds the tainted mark, so forcing it would re-reference the
+            // very corruption being recovered from — and the frame must not ship tagged
+            // `recovery_anchor` either (the client lifts its post-loss freeze on that tag).
             if let Some(slot) = self.pending_force.take() {
-                force_slot = Some(slot);
+                if self.ltr_slots[slot].is_some() {
-                recovery_anchor = true;
+                    force_slot = Some(slot);
+                    recovery_anchor = true;
+                }
             }
             // Mark cadence: refresh a long-term reference on every IDR and every `ltr_mark_interval`
             // frames — but never on the recovery frame itself (marking rotates `next_ltr_slot` and
@@ -2363,6 +2369,16 @@ impl Encoder for AmfEncoder {
         if !self.ltr_active || first < 0 || first > last {
             return false;
         }
+        // Taint sweep BEFORE picking the anchor: an LTR marked at-or-after the loss start was
+        // encoded inside the client's corrupt window — the client either never received it or
+        // decoded it against a broken reference chain. Serving it as "known-good" on a LATER
+        // loss ships corruption as the recovery anchor (and every subsequent mark re-samples
+        // it). Dropped slots stay dropped; the cadence re-marks a clean frame within ~1/4 s.
+        for marked in self.ltr_slots.iter_mut() {
+            if marked.is_some_and(|idx| idx >= first) {
+                *marked = None;
+            }
+        }
         // Pick the newest LTR strictly OLDER than the loss: the most recent known-good reference the
         // client still holds, so re-referencing it costs the least (smallest recovery-frame residual).
         // `ltr_slots` store the WIRE frame index of the marked frame (`submit_indexed` pins
@@ -2391,6 +2407,9 @@ impl Encoder for AmfEncoder {
                 true
             }
             None => {
+                // The sweep may have emptied the slot an earlier (un-consumed) force pointed
+                // at — clear it so the next submit can't force-reference a tainted hardware slot.
+                self.pending_force = None;
                 tracing::info!(
                     first,
                     last,

crates/pf-encode/src/enc/windows/qsv.rs

@@ -1017,7 +1017,7 @@ impl Encoder for QsvEncoder {
         self.frame_idx += 1;
         // --- LTR-RFI per-frame decisions (the AMF policy verbatim; see that module's doc) ---
         let mut mark_slot: Option<usize> = None;
-        let mut force_slot: Option<usize> = None;
+        let mut force_ltr: Option<(usize, i64)> = None;
         let mut recovery_anchor = false;
         if self.ltr_active {
             if forced {
@@ -1035,10 +1035,16 @@ impl Encoder for QsvEncoder {
                 );
             }
             if let Some(slot) = self.pending_force.take() {
-                force_slot = Some(slot);
+                // Resolve the anchor NOW: a taint sweep in `invalidate_ref_frames` may have
-                recovery_anchor = true;
+                // emptied the slot since the force was queued. An empty slot means there is
+                // nothing clean to re-reference — the frame must ship as a plain P WITHOUT the
+                // `recovery_anchor` tag (the client lifts its post-loss freeze on that tag).
+                if let Some(idx) = self.ltr_slots[slot] {
+                    force_ltr = Some((slot, idx));
+                    recovery_anchor = true;
+                }
             }
-            if force_slot.is_none() && (forced || cur_idx % self.ltr_mark_interval == 0) {
+            if force_ltr.is_none() && (forced || cur_idx % self.ltr_mark_interval == 0) {
                 let slot = self.next_ltr_slot;
                 self.ltr_slots[slot] = Some(cur_idx);
                 self.next_ltr_slot = (self.next_ltr_slot + 1) % NUM_LTR_SLOTS;
@@ -1046,6 +1052,7 @@ impl Encoder for QsvEncoder {
             }
         }
         let ltr_slots = self.ltr_slots;
+        let reject_ok = self.codec != Codec::Av1;
         let inner = self.inner.as_mut().expect("ensure_inner succeeded");
         // Bound the in-flight window BEFORE submitting: drain finished AUs (buffered for
         // `poll`) instead of letting the queue grow under overload.
@@ -1130,7 +1137,7 @@ impl Encoder for QsvEncoder {
                 (*surf).Data.TimeStamp = captured.pts_ns.wrapping_mul(9) / 100_000; // 90 kHz
                                                                                     // Per-frame control: forced IDR and/or the LTR reflist.
                 let mut ctrl: Option<Box<FrameCtrl>> = None;
-                if forced || mark_slot.is_some() || force_slot.is_some() {
+                if forced || mark_slot.is_some() || force_ltr.is_some() {
                     let mut c = FrameCtrl::new();
                     if forced {
                         c.ctrl.FrameType = (vpl::MFX_FRAMETYPE_IDR
@@ -1148,24 +1155,55 @@ impl Encoder for QsvEncoder {
                         c.reflist.ApplyLongTermIdx = 1;
                         use_reflist = true;
                     }
-                    if let Some(slot) = force_slot {
+                    if let Some((slot, ltr_frame)) = force_ltr {
-                        if let Some(ltr_frame) = ltr_slots[slot] {
+                        // Force THIS frame to predict only from the known-good LTR — the
-                            // Force THIS frame to predict only from the known-good LTR — the
+                        // clean re-anchor. LongTermIdx stays 0 inside PreferredRefList
-                            // clean re-anchor. LongTermIdx stays 0 inside PreferredRefList
+                        // (the AV1 runtime rejects nonzero there; AVC/HEVC key on
-                            // (the AV1 runtime rejects nonzero there; AVC/HEVC key on
+                        // FrameOrder).
-                            // FrameOrder).
+                        c.reflist.PreferredRefList[0].FrameOrder = ltr_frame as u32;
-                            c.reflist.PreferredRefList[0].FrameOrder = ltr_frame as u32;
+                        c.reflist.PreferredRefList[0].PicStruct =
-                            c.reflist.PreferredRefList[0].PicStruct =
+                            vpl::MFX_PICSTRUCT_PROGRESSIVE as u16;
-                                vpl::MFX_PICSTRUCT_PROGRESSIVE as u16;
+                        // A preference alone is a reorder HINT (VPL spec) — the encoder may
-                            use_reflist = true;
+                        // still predict from the tainted short-term refs alongside it. AMF's
-                            tracing::info!(
+                        // ForceLTRReferenceBitfield and NVENC's invalidation are hard
-                                slot,
+                        // exclusions; emulate that here by rejecting every other DPB
-                                ltr_frame,
+                        // candidate — the short-term sliding window (the 2 most recent
-                                frame = cur_idx,
+                        // frames) and the other LTR slot — and capping L0 at one active
-                                "QSV LTR-RFI: re-referencing known-good LTR (clean recovery, \
+                        // entry. Without this the "clean recovery" frame can carry the
-                                 no IDR)"
+                        // corruption forward, which the client cannot detect (the field
-                            );
+                        // failure: permanent macroblock soup under sustained loss).
+                        // AVC/HEVC only: the AV1 runtime's universal-reflist rejection path
+                        // is unvalidated, and an unhonored hint there still converges via
+                        // the host's IDR escalation.
+                        if reject_ok {
+                            let mut rej = 0;
+                            let mut reject = |idx: i64| {
+                                if idx >= 0 && idx != ltr_frame {
+                                    c.reflist.RejectedRefList[rej].FrameOrder = idx as u32;
+                                    c.reflist.RejectedRefList[rej].PicStruct =
+                                        vpl::MFX_PICSTRUCT_PROGRESSIVE as u16;
+                                    rej += 1;
+                                }
+                            };
+                            reject(cur_idx - 1);
+                            reject(cur_idx - 2);
+                            for (s, marked) in ltr_slots.iter().enumerate() {
+                                if s != slot {
+                                    if let Some(idx) = *marked {
+                                        reject(idx);
+                                    }
+                                }
+                            }
+                            c.reflist.NumRefIdxL0Active = 1;
                         }
+                        use_reflist = true;
+                        tracing::info!(
+                            slot,
+                            ltr_frame,
+                            frame = cur_idx,
+                            "QSV LTR-RFI: re-referencing known-good LTR (clean recovery, \
+                             no IDR)"
+                        );
                     }
                     if use_reflist {
                         c.attach_reflist();
@@ -1265,6 +1303,17 @@ impl Encoder for QsvEncoder {
         if !self.ltr_active || first < 0 || first > last {
             return false;
         }
+        // Taint sweep BEFORE picking the anchor: an LTR marked at-or-after the loss start was
+        // encoded inside the client's corrupt window — the client either never received it or
+        // decoded it against a broken reference chain. Serving it as "known-good" on a LATER
+        // loss ships corruption as the recovery anchor, and every subsequent mark re-samples
+        // the soup — the sustained-loss field failure where the picture never healed. Dropped
+        // slots stay dropped; the cadence re-marks a clean frame within ~1/4 s.
+        for marked in self.ltr_slots.iter_mut() {
+            if marked.is_some_and(|idx| idx >= first) {
+                *marked = None;
+            }
+        }
         let mut best: Option<(usize, i64)> = None;
         for (slot, marked) in self.ltr_slots.iter().enumerate() {
             if let Some(idx) = *marked {
@@ -1287,6 +1336,9 @@ impl Encoder for QsvEncoder {
                 true
             }
             None => {
+                // The sweep may have emptied the slot an earlier (un-consumed) force pointed
+                // at — clear it so the next submit can't half-apply a stale recovery.
+                self.pending_force = None;
                 tracing::info!(
                     first,
                     last,
@@ -1845,6 +1897,36 @@ mod tests {
         );
     }
 
+    /// Taint sweep: a loss that predates every live LTR mark leaves NO clean anchor — every
+    /// slot was marked inside the client's corrupt window. The invalidate must decline (the
+    /// caller then serves the IDR) and no recovery_anchor AU may ship; before the sweep this
+    /// force-referenced a tainted mark and shipped corruption tagged as a clean recovery.
+    #[test]
+    fn qsv_live_ltr_rfi_taint_sweep_declines() {
+        let mut rfi_answered = None;
+        let Some(aus) = drive_live(Codec::H264, false, 60, |enc, i| {
+            if i == 30 && enc.caps().supports_rfi {
+                // Frame 0 lost: the IDR itself — every mark (0, 15, ...) is at-or-after it.
+                rfi_answered = Some(enc.invalidate_ref_frames(0, 2));
+            }
+        }) else {
+            return;
+        };
+        assert_stream_shape(&aus, 60, true);
+        let Some(answered) = rfi_answered else {
+            eprintln!("note: driver declined LTR (supports_rfi=false) — sweep not exercised");
+            return;
+        };
+        assert!(
+            !answered,
+            "a loss covering every live LTR mark must fall back to IDR recovery"
+        );
+        assert!(
+            !aus.iter().any(|a| a.recovery_anchor),
+            "no recovery_anchor AU may ship when the sweep left no clean LTR"
+        );
+    }
+
     /// No-IDR bitrate retarget — Phase 3 on-glass: `reconfigure_bitrate` mid-stream must be
     /// accepted (HRD off + StartNewSequence=OFF) and must not emit a keyframe.
     #[test]

crates/punktfunk-host/src/native/stream.rs

@@ -1166,6 +1166,21 @@ pub(super) fn virtual_stream(ctx: SessionContext, prepared: Option<PreparedDispl
     // clock now — that coalesces the keyframe storm a client fires while its decoder wedges on the cold
     // opening GOP, instead of answering it with a redundant second IDR.
     let mut last_forced_idr: Option<std::time::Instant> = Some(std::time::Instant::now());
+    // A successful LTR-RFI recovery anchors THIS clock, not the IDR cooldown: it justifies
+    // swallowing the client's `frames_dropped`-driven echo of the SAME loss (arriving ~one
+    // loss-window later), but must never indefinitely defer the client's ESCALATION — a
+    // keyframe request that keeps coming because the RFI recovery did not actually heal its
+    // decoder. Re-anchoring the full IDR cooldown here (the old behavior) livelocked under
+    // sustained loss: each new loss → RFI → cooldown re-anchored → the wedged client's IDR
+    // pleas coalesced away forever, and the picture never recovered (the lid-closed Intel
+    // laptop field report: permanent macroblock soup, dozens of swallowed requests per IDR).
+    let mut last_rfi: Option<std::time::Instant> = None;
+    // Keyframe requests swallowed on RFI-echo grounds since the last real IDR / quiet period.
+    // Capped: requests past the cap mean RFI is not healing this client — escalate to the IDR.
+    let mut rfi_echo_swallowed: u32 = 0;
+    // When the previous keyframe request arrived — a long quiet gap means the client healed
+    // and the next request opens a NEW loss episode (the echo-swallow budget resets).
+    let mut last_kf_request: Option<std::time::Instant> = None;
     // Self-diagnosis for the periodic-stutter class: warns when the served recovery IDRs settle
     // into a stable multi-second rhythm (see [`pf_frame::metronome::Metronome`]).
     let mut recovery_cadence = pf_frame::metronome::Metronome::new();
@@ -1536,11 +1551,12 @@ pub(super) fn virtual_stream(ctx: SessionContext, prepared: Option<PreparedDispl
                 } else if enc.caps().supports_rfi
                     && enc.invalidate_ref_frames(first as i64, last as i64)
                 {
-                    // The RFI recovered the loss with a clean re-anchor P-frame (no IDR). Anchor the
+                    // The RFI recovered the loss with a clean re-anchor P-frame (no IDR). Anchor
-                    // keyframe cooldown so the client's echo of the SAME loss — its frames_dropped-
+                    // the RFI-echo window (NOT the IDR cooldown — see `last_rfi`) so the client's
-                    // driven keyframe request, arriving ~one loss-window later — is coalesced away
+                    // echo of the SAME loss — its frames_dropped-driven keyframe request, arriving
-                    // instead of emitting a redundant full IDR right after the cheap recovery.
+                    // ~one loss-window later — is coalesced away instead of emitting a redundant
-                    last_forced_idr = Some(std::time::Instant::now());
+                    // full IDR right after the cheap recovery.
+                    last_rfi = Some(std::time::Instant::now());
                 } else {
                     want_kf = true; // range too old / no RFI backend → coalesced keyframe below
                 }
@@ -1562,19 +1578,46 @@ pub(super) fn virtual_stream(ctx: SessionContext, prepared: Option<PreparedDispl
             // promptly.
             const IDR_COOLDOWN_INTRA: std::time::Duration = std::time::Duration::from_secs(2);
             const IDR_COOLDOWN_FULL: std::time::Duration = std::time::Duration::from_millis(750);
+            // The RFI-echo window: how long after a successful LTR-RFI recovery a keyframe
+            // request is presumed to be the client's echo of the SAME loss (the recovery frame
+            // is still in flight / just decoding) rather than an escalation. Field data: the
+            // echo lands ~110-130 ms after the RFI on a LAN-ish RTT.
+            const RFI_ECHO_WINDOW: std::time::Duration = std::time::Duration::from_millis(300);
+            // How many requests the echo window may swallow per loss episode. Requests past
+            // this budget mean the LTR-RFI recoveries are NOT healing the client (anchor lost,
+            // or corrupt client-side) — serve the IDR it is asking for. Without the cap, a
+            // sustained-loss session (RFI every few hundred ms, each re-opening the window)
+            // suppressed the client's escalation indefinitely.
+            const RFI_ECHO_MAX_SWALLOWED: u32 = 2;
+            // A quiet gap since the last keyframe request = the client healed; the next
+            // request opens a NEW loss episode with a fresh echo-swallow budget.
+            const KF_EPISODE_RESET: std::time::Duration = std::time::Duration::from_secs(1);
             let window = if enc.caps().intra_refresh {
                 IDR_COOLDOWN_INTRA
             } else {
                 IDR_COOLDOWN_FULL
             };
-            let suppress = last_forced_idr.is_some_and(|t| t.elapsed() < window);
+            let now = std::time::Instant::now();
-            if suppress {
+            if last_kf_request.is_some_and(|t| now.duration_since(t) > KF_EPISODE_RESET) {
+                rfi_echo_swallowed = 0;
+            }
+            last_kf_request = Some(now);
+            let idr_recent = last_forced_idr.is_some_and(|t| t.elapsed() < window);
+            let rfi_echo = last_rfi.is_some_and(|t| t.elapsed() < RFI_ECHO_WINDOW)
+                && rfi_echo_swallowed < RFI_ECHO_MAX_SWALLOWED;
+            if idr_recent {
                 tracing::debug!("keyframe request coalesced — within the IDR cooldown");
+            } else if rfi_echo {
+                rfi_echo_swallowed += 1;
+                tracing::debug!(
+                    swallowed = rfi_echo_swallowed,
+                    "keyframe request coalesced — echo of an RFI-recovered loss"
+                );
             } else {
                 tracing::debug!("forcing keyframe (client decode recovery)");
                 enc.request_keyframe();
-                let now = std::time::Instant::now();
                 last_forced_idr = Some(now);
+                rfi_echo_swallowed = 0; // the IDR resets the episode — echoes of IT coalesce via the cooldown
                 if let Some(period) = recovery_cadence.note(now) {
                     tracing::warn!(
                         period_s = format!("{:.1}", period.as_secs_f64()),