fix(video): add frame metadata and Android encode diagnostics

crates/wzp-client/src/analyzer.rs

@@ -243,6 +243,7 @@ struct VideoStreamProbe {
     last_frame: Option<Instant>,
     reassembler: VideoReassembler,
     decoder: Option<Box<dyn VideoDecoder>>,
+    decoder_key: Option<(CodecId, u32, u32)>,
     decode_ok: u64,
     decode_pending: u64,
     decode_err: u64,
@@ -275,6 +276,7 @@ impl VideoStreamProbe {
             last_frame: None,
             reassembler: VideoReassembler::new(),
             decoder,
+            decoder_key: decode.then_some((codec, 1280, 720)),
             decode_ok: 0,
             decode_pending: 0,
             decode_err: 0,
@@ -294,6 +296,7 @@ impl VideoStreamProbe {
                 .is_some()
                 .then(|| create_video_decoder(self.codec, 1280, 720).ok())
                 .flatten();
+            self.decoder_key = self.decoder.as_ref().map(|_| (self.codec, 1280, 720));
         }
         if self.seq_initialized {
             let expected = self.last_seq.wrapping_add(1);
@@ -305,19 +308,26 @@ impl VideoStreamProbe {
         self.last_seq = pkt.header.seq;
         self.seq_initialized = true;
 
-        if let Some((codec, keyframe, frame)) = self.reassembler.push(pkt) {
+        if let Some(frame) = self.reassembler.push(pkt) {
             self.frames += 1;
-            self.bytes += frame.len() as u64;
-            self.max_frame_bytes = self.max_frame_bytes.max(frame.len());
+            self.bytes += frame.data.len() as u64;
+            self.max_frame_bytes = self.max_frame_bytes.max(frame.data.len());
             self.last_frame = Some(now);
-            if keyframe {
+            if frame.is_keyframe {
                 self.keyframes += 1;
             }
-            if codec != self.codec {
-                self.codec = codec;
+            if frame.codec_id != self.codec {
+                self.codec = frame.codec_id;
+            }
+            let frame_width = frame.width.unwrap_or(1280) as u32;
+            let frame_height = frame.height.unwrap_or(720) as u32;
+            let decoder_key = (self.codec, frame_width, frame_height);
+            if self.decoder.is_some() && self.decoder_key != Some(decoder_key) {
+                self.decoder = create_video_decoder(self.codec, frame_width, frame_height).ok();
+                self.decoder_key = self.decoder.as_ref().map(|_| decoder_key);
             }
             if let Some(decoder) = self.decoder.as_mut() {
-                match decoder.decode(&frame) {
+                match decoder.decode(&frame.data) {
                     Ok(Some(decoded)) => {
                         self.decode_ok += 1;
                         self.last_decode_debug = decoder.debug_snapshot();

crates/wzp-video/src/encoder.rs

@@ -49,6 +49,11 @@ pub trait VideoEncoder: Send {
     ///
     /// Default implementation is a no-op.
     fn set_mode(&mut self, _mode: crate::EncoderMode) {}
+
+    /// Optional platform-specific encoder state for debug logs.
+    fn debug_snapshot(&self) -> Option<String> {
+        None
+    }
 }
 
 /// Raw video frame input for encoding.

crates/wzp-video/src/mediacodec.rs

@@ -27,6 +27,8 @@ pub struct MediaCodecEncoder {
     width: u32,
     #[cfg(target_os = "android")]
     height: u32,
+    #[cfg(target_os = "android")]
+    input_format_logged: bool,
     force_keyframe: bool,
     #[cfg(not(target_os = "android"))]
     _width: u32,
@@ -86,6 +88,7 @@ impl MediaCodecEncoder {
                 codec,
                 width,
                 height,
+                input_format_logged: false,
                 force_keyframe: false,
             })
         }
@@ -123,8 +126,34 @@ impl VideoEncoder for MediaCodecEncoder {
                     if self.force_keyframe {
                         self.request_sync_frame();
                     }
-                    let input =
-                        i420_to_nv12(&frame.data, self.width as usize, self.height as usize)?;
+                    let layout = encoder_input_layout(&self.codec, self.width, self.height);
+                    if !self.input_format_logged {
+                        self.input_format_logged = true;
+                        log_media_codec_input_format("h264_encoder_input", &self.codec, &layout);
+                    }
+                    let input_capacity = { buffer.buffer_mut().len() };
+                    let mut input = i420_to_padded_nv12(
+                        &frame.data,
+                        self.width as usize,
+                        self.height as usize,
+                        layout.stride,
+                        layout.slice_height,
+                    )?;
+                    if input.len() > input_capacity {
+                        tracing::warn!(
+                            target: "wzp_video::mediacodec",
+                            padded_len = input.len(),
+                            input_capacity,
+                            "MediaCodec H.264 input buffer smaller than padded layout; falling back to tight NV12"
+                        );
+                        input = i420_to_padded_nv12(
+                            &frame.data,
+                            self.width as usize,
+                            self.height as usize,
+                            self.width as usize,
+                            self.height as usize,
+                        )?;
+                    }
                     let to_copy = {
                         let buf = buffer.buffer_mut();
                         let n = input.len().min(buf.len());
@@ -398,6 +427,8 @@ pub struct MediaCodecHevcEncoder {
     width: u32,
     #[cfg(target_os = "android")]
     height: u32,
+    #[cfg(target_os = "android")]
+    input_format_logged: bool,
     force_keyframe: bool,
     #[cfg(not(target_os = "android"))]
     _width: u32,
@@ -439,6 +470,7 @@ impl MediaCodecHevcEncoder {
                 codec,
                 width,
                 height,
+                input_format_logged: false,
                 force_keyframe: false,
             })
         }
@@ -476,10 +508,38 @@ impl VideoEncoder for MediaCodecHevcEncoder {
                     } else {
                         0
                     };
+                    let layout = encoder_input_layout(&self.codec, self.width, self.height);
+                    if !self.input_format_logged {
+                        self.input_format_logged = true;
+                        log_media_codec_input_format("hevc_encoder_input", &self.codec, &layout);
+                    }
+                    let input_capacity = { buffer.buffer_mut().len() };
+                    let mut input = i420_to_padded_planar(
+                        &frame.data,
+                        self.width as usize,
+                        self.height as usize,
+                        layout.stride,
+                        layout.slice_height,
+                    )?;
+                    if input.len() > input_capacity {
+                        tracing::warn!(
+                            target: "wzp_video::mediacodec",
+                            padded_len = input.len(),
+                            input_capacity,
+                            "MediaCodec HEVC input buffer smaller than padded layout; falling back to tight I420"
+                        );
+                        input = i420_to_padded_planar(
+                            &frame.data,
+                            self.width as usize,
+                            self.height as usize,
+                            self.width as usize,
+                            self.height as usize,
+                        )?;
+                    }
                     let to_copy = {
                         let buf = buffer.buffer_mut();
-                        let n = frame.data.len().min(buf.len());
-                        for (d, &s) in buf[..n].iter_mut().zip(frame.data[..n].iter()) {
+                        let n = input.len().min(buf.len());
+                        for (d, &s) in buf[..n].iter_mut().zip(input[..n].iter()) {
                             d.write(s);
                         }
                         n
@@ -1153,6 +1213,46 @@ fn positive_format_usize(format: &MediaFormat, key: &str) -> Option<usize> {
     (value > 0).then_some(value as usize)
 }
 
+#[cfg(target_os = "android")]
+#[derive(Clone, Copy, Debug)]
+struct EncoderInputLayout {
+    stride: usize,
+    slice_height: usize,
+}
+
+#[cfg(target_os = "android")]
+fn encoder_input_layout(codec: &MediaCodec, width: u32, height: u32) -> EncoderInputLayout {
+    // ndk 0.9 exposes AMediaCodec_getInputFormat only behind API 28, while
+    // this app still targets API 26. Keep encoder input tight until we can
+    // query the actual input format. Guessing padded rows here is dangerous:
+    // when the encoder actually reads tight input, padding bytes become pixels
+    // from the next row and show up as diagonal green bands.
+    let _ = codec;
+    let width = width as usize;
+    let height = height as usize;
+    EncoderInputLayout {
+        stride: width,
+        slice_height: height,
+    }
+}
+
+#[cfg(target_os = "android")]
+fn log_media_codec_input_format(label: &str, codec: &MediaCodec, layout: &EncoderInputLayout) {
+    let format = codec.output_format();
+    tracing::info!(
+        target: "wzp_video::mediacodec",
+        label,
+        color_format = format.i32("color-format"),
+        width = format.i32("width"),
+        height = format.i32("height"),
+        stride = format.i32("stride"),
+        slice_height = format.i32("slice-height"),
+        effective_stride = layout.stride,
+        effective_slice_height = layout.slice_height,
+        "MediaCodec input format"
+    );
+}
+
 #[cfg(target_os = "android")]
 fn log_media_codec_format(label: &str, codec: &MediaCodec) {
     let format = codec.output_format();
@@ -1183,7 +1283,13 @@ fn i420_len(width: usize, height: usize) -> Result<usize, VideoError> {
 }
 
 #[cfg(target_os = "android")]
-fn i420_to_nv12(src: &[u8], width: usize, height: usize) -> Result<Vec<u8>, VideoError> {
+fn i420_to_padded_nv12(
+    src: &[u8],
+    width: usize,
+    height: usize,
+    stride: usize,
+    slice_height: usize,
+) -> Result<Vec<u8>, VideoError> {
     let y_size = width.checked_mul(height).ok_or_else(|| {
         VideoError::InvalidInput(format!("invalid frame dimensions {width}x{height}"))
     })?;
@@ -1196,17 +1302,127 @@ fn i420_to_nv12(src: &[u8], width: usize, height: usize) -> Result<Vec<u8>, Vide
         )));
     }
 
-    let mut out = vec![0u8; expected];
-    out[..y_size].copy_from_slice(&src[..y_size]);
+    if stride < width || slice_height < height {
+        return Err(VideoError::InvalidInput(format!(
+            "invalid encoder input layout {stride}x{slice_height} for {width}x{height}"
+        )));
+    }
+
+    let chroma_width = width / 2;
+    let chroma_height = height / 2;
+    let y_stride = stride;
+    let uv_stride = stride;
+    let y_slice_height = slice_height;
+    let uv_slice_height = (slice_height / 2).max(chroma_height);
+    let y_padded_size = y_stride.checked_mul(y_slice_height).ok_or_else(|| {
+        VideoError::InvalidInput(format!(
+            "invalid padded Y layout {y_stride}x{y_slice_height}"
+        ))
+    })?;
+    let uv_padded_size = uv_stride.checked_mul(uv_slice_height).ok_or_else(|| {
+        VideoError::InvalidInput(format!(
+            "invalid padded UV layout {uv_stride}x{uv_slice_height}"
+        ))
+    })?;
+    let total = y_padded_size
+        .checked_add(uv_padded_size)
+        .ok_or_else(|| VideoError::InvalidInput("padded NV12 size overflow".into()))?;
+
+    let mut out = vec![0u8; total];
+    out[y_padded_size..].fill(128);
+    for row in 0..height {
+        let src_off = row * width;
+        let dst_off = row * y_stride;
+        out[dst_off..dst_off + width].copy_from_slice(&src[src_off..src_off + width]);
+    }
+
     let u = &src[y_size..y_size + uv_size];
     let v = &src[y_size + uv_size..y_size + uv_size * 2];
-    for i in 0..uv_size {
-        out[y_size + i * 2] = u[i];
-        out[y_size + i * 2 + 1] = v[i];
+    for row in 0..chroma_height {
+        let src_row = row * chroma_width;
+        let dst_row = y_padded_size + row * uv_stride;
+        for col in 0..chroma_width {
+            out[dst_row + col * 2] = u[src_row + col];
+            out[dst_row + col * 2 + 1] = v[src_row + col];
+        }
     }
     Ok(out)
 }
 
+#[cfg(target_os = "android")]
+fn i420_to_padded_planar(
+    src: &[u8],
+    width: usize,
+    height: usize,
+    stride: usize,
+    slice_height: usize,
+) -> Result<Vec<u8>, VideoError> {
+    let y_size = width.checked_mul(height).ok_or_else(|| {
+        VideoError::InvalidInput(format!("invalid frame dimensions {width}x{height}"))
+    })?;
+    let uv_size = y_size / 4;
+    let expected = y_size + uv_size * 2;
+    if src.len() < expected {
+        return Err(VideoError::InvalidInput(format!(
+            "I420 frame too small for padded planar copy: {} bytes, expected {expected}",
+            src.len()
+        )));
+    }
+    if stride < width || slice_height < height {
+        return Err(VideoError::InvalidInput(format!(
+            "invalid encoder input layout {stride}x{slice_height} for {width}x{height}"
+        )));
+    }
+
+    let chroma_width = width / 2;
+    let chroma_height = height / 2;
+    let y_stride = stride;
+    let chroma_stride = (stride / 2).max(chroma_width);
+    let y_slice_height = slice_height;
+    let chroma_slice_height = (slice_height / 2).max(chroma_height);
+    let y_padded_size = y_stride.checked_mul(y_slice_height).ok_or_else(|| {
+        VideoError::InvalidInput(format!(
+            "invalid padded Y layout {y_stride}x{y_slice_height}"
+        ))
+    })?;
+    let chroma_padded_size = chroma_stride
+        .checked_mul(chroma_slice_height)
+        .ok_or_else(|| {
+            VideoError::InvalidInput(format!(
+                "invalid padded chroma layout {chroma_stride}x{chroma_slice_height}"
+            ))
+        })?;
+    let chroma_total = chroma_padded_size
+        .checked_mul(2)
+        .ok_or_else(|| VideoError::InvalidInput("padded I420 chroma size overflow".into()))?;
+    let total = y_padded_size
+        .checked_add(chroma_total)
+        .ok_or_else(|| VideoError::InvalidInput("padded I420 size overflow".into()))?;
+
+    let mut out = vec![0u8; total];
+    out[y_padded_size..].fill(128);
+    for row in 0..height {
+        let src_off = row * width;
+        let dst_off = row * y_stride;
+        out[dst_off..dst_off + width].copy_from_slice(&src[src_off..src_off + width]);
+    }
+
+    let src_u = y_size;
+    let src_v = y_size + uv_size;
+    let dst_u = y_padded_size;
+    let dst_v = y_padded_size + chroma_padded_size;
+    for row in 0..chroma_height {
+        let src_off = row * chroma_width;
+        let dst_off = row * chroma_stride;
+        out[dst_u + dst_off..dst_u + dst_off + chroma_width]
+            .copy_from_slice(&src[src_u + src_off..src_u + src_off + chroma_width]);
+        out[dst_v + dst_off..dst_v + dst_off + chroma_width]
+            .copy_from_slice(&src[src_v + src_off..src_v + src_off + chroma_width]);
+    }
+
+    Ok(out)
+}
+
 #[cfg(target_os = "android")]
 fn yuv420_planar_to_tight_i420(
     src: &[u8],
@@ -1410,7 +1626,7 @@ fn split_annex_b(data: &[u8]) -> Vec<&[u8]> {
 /// Android MediaCodec `csd-0`.
 #[allow(dead_code)]
 fn extract_sequence_header_obu(data: &[u8]) -> Option<Vec<u8>> {
-    use crate::av1_obu::{ObuHeader, read_leb128};
+    use crate::av1_obu::{read_leb128, ObuHeader};
     let mut i = 0usize;
     while i < data.len() {
         let header = ObuHeader::from_byte(data[i]);

crates/wzp-video/src/transport.rs

@@ -28,6 +28,24 @@ use wzp_proto::{CodecId, MediaHeaderV2, MediaPacket, MediaType};
 /// 1200 (QUIC MTU) − 16 (MediaHeaderV2) − 16 (AEAD tag) = 1168.
 pub const VIDEO_MAX_PAYLOAD: usize = 1168;
 
+const VIDEO_FRAME_META_MAGIC: [u8; 4] = *b"WZV1";
+const VIDEO_FRAME_META_LEN: usize = 8;
+
+#[derive(Clone, Copy, Debug, PartialEq, Eq)]
+pub struct VideoFrameMeta {
+    pub width: u16,
+    pub height: u16,
+}
+
+#[derive(Clone, Debug, PartialEq, Eq)]
+pub struct ReassembledVideoFrame {
+    pub codec_id: CodecId,
+    pub is_keyframe: bool,
+    pub width: Option<u16>,
+    pub height: Option<u16>,
+    pub data: Vec<u8>,
+}
+
 /// Fragments one encoded video frame into a sequence of [`MediaPacket`]s.
 ///
 /// Pass each `MediaPacket` to `transport.send_media()`.
@@ -37,12 +55,20 @@ pub fn packetize_video_frame(
     is_keyframe: bool,
     seq: &mut u32,
     timestamp_ms: u32,
+    width: u32,
+    height: u32,
 ) -> Vec<MediaPacket> {
     if frame.is_empty() {
         return vec![];
     }
 
-    let chunks: Vec<&[u8]> = frame.chunks(VIDEO_MAX_PAYLOAD).collect();
+    let mut framed = Vec::with_capacity(VIDEO_FRAME_META_LEN + frame.len());
+    framed.extend_from_slice(&VIDEO_FRAME_META_MAGIC);
+    framed.extend_from_slice(&(width.min(u16::MAX as u32) as u16).to_be_bytes());
+    framed.extend_from_slice(&(height.min(u16::MAX as u32) as u16).to_be_bytes());
+    framed.extend_from_slice(frame);
+
+    let chunks: Vec<&[u8]> = framed.chunks(VIDEO_MAX_PAYLOAD).collect();
     let total = chunks.len().min(255);
     let mut packets = Vec::with_capacity(total);
 
@@ -118,9 +144,8 @@ impl VideoReassembler {
 
     /// Push one received video packet.
     ///
-    /// Returns `Some((codec_id, is_keyframe, frame_bytes))` when a complete
-    /// frame is ready, `None` otherwise.
-    pub fn push(&mut self, pkt: &MediaPacket) -> Option<(CodecId, bool, Vec<u8>)> {
+    /// Returns `Some(frame)` when a complete frame is ready, `None` otherwise.
+    pub fn push(&mut self, pkt: &MediaPacket) -> Option<ReassembledVideoFrame> {
         let hdr = &pkt.header;
         let fragment_index = (hdr.fec_block >> 8) as u8;
         let fragment_count = (hdr.fec_block & 0xFF) as u8;
@@ -161,7 +186,14 @@ impl VideoReassembler {
         for i in 0..total as u8 {
             frame.extend_from_slice(pending.fragments.get(&i)?);
         }
-        Some((codec_id, pending.is_keyframe, frame))
+        let (meta, data) = split_video_frame_payload(frame);
+        Some(ReassembledVideoFrame {
+            codec_id,
+            is_keyframe: pending.is_keyframe,
+            width: meta.map(|m| m.width),
+            height: meta.map(|m| m.height),
+            data,
+        })
     }
 
     /// Evict stale pending frames older than `max_age_ms` milliseconds.
@@ -169,12 +201,22 @@ impl VideoReassembler {
     /// Call periodically (e.g. every 2s) to prevent accumulation of frames
     /// whose first or middle fragments were lost.
     pub fn evict_stale(&mut self, current_timestamp_ms: u32, max_age_ms: u32) {
-        self.pending.retain(|&ts, _| {
-            current_timestamp_ms.wrapping_sub(ts) <= max_age_ms
-        });
+        self.pending
+            .retain(|&ts, _| current_timestamp_ms.wrapping_sub(ts) <= max_age_ms);
     }
 }
 
+fn split_video_frame_payload(mut frame: Vec<u8>) -> (Option<VideoFrameMeta>, Vec<u8>) {
+    if frame.len() < VIDEO_FRAME_META_LEN || frame[..4] != VIDEO_FRAME_META_MAGIC {
+        return (None, frame);
+    }
+
+    let width = u16::from_be_bytes([frame[4], frame[5]]);
+    let height = u16::from_be_bytes([frame[6], frame[7]]);
+    frame.drain(..VIDEO_FRAME_META_LEN);
+    (Some(VideoFrameMeta { width, height }), frame)
+}
+
 impl Default for VideoReassembler {
     fn default() -> Self {
         Self::new()
@@ -193,7 +235,7 @@ mod tests {
     fn single_fragment_roundtrip() {
         let frame = make_frame(100);
         let mut seq = 0u32;
-        let pkts = packetize_video_frame(&frame, CodecId::Av1Main, true, &mut seq, 1000);
+        let pkts = packetize_video_frame(&frame, CodecId::Av1Main, true, &mut seq, 1000, 640, 480);
         assert_eq!(pkts.len(), 1);
         assert!(pkts[0].header.is_keyframe());
         assert!(pkts[0].header.is_frame_end());
@@ -203,17 +245,27 @@ mod tests {
         let mut reassembler = VideoReassembler::new();
         let result = reassembler.push(&pkts[0]);
         assert!(result.is_some());
-        let (codec, is_kf, data) = result.unwrap();
-        assert_eq!(codec, CodecId::Av1Main);
-        assert!(is_kf);
-        assert_eq!(data, frame);
+        let result = result.unwrap();
+        assert_eq!(result.codec_id, CodecId::Av1Main);
+        assert!(result.is_keyframe);
+        assert_eq!(result.width, Some(640));
+        assert_eq!(result.height, Some(480));
+        assert_eq!(result.data, frame);
     }
 
     #[test]
     fn multi_fragment_roundtrip() {
         let frame = make_frame(VIDEO_MAX_PAYLOAD * 3 + 50);
         let mut seq = 0u32;
-        let pkts = packetize_video_frame(&frame, CodecId::H264Baseline, false, &mut seq, 2000);
+        let pkts = packetize_video_frame(
+            &frame,
+            CodecId::H264Baseline,
+            false,
+            &mut seq,
+            2000,
+            960,
+            540,
+        );
         assert_eq!(pkts.len(), 4);
         assert!(!pkts[0].header.is_frame_end());
         assert!(pkts[3].header.is_frame_end());
@@ -224,33 +276,66 @@ mod tests {
         for pkt in &pkts {
             result = reassembler.push(pkt);
         }
-        let (codec, is_kf, data) = result.unwrap();
-        assert_eq!(codec, CodecId::H264Baseline);
-        assert!(!is_kf);
-        assert_eq!(data, frame);
+        let result = result.unwrap();
+        assert_eq!(result.codec_id, CodecId::H264Baseline);
+        assert!(!result.is_keyframe);
+        assert_eq!(result.width, Some(960));
+        assert_eq!(result.height, Some(540));
+        assert_eq!(result.data, frame);
     }
 
     #[test]
     fn out_of_order_delivery() {
         let frame = make_frame(VIDEO_MAX_PAYLOAD * 2 + 100);
         let mut seq = 0u32;
-        let pkts = packetize_video_frame(&frame, CodecId::Av1Main, false, &mut seq, 3000);
+        let pkts = packetize_video_frame(&frame, CodecId::Av1Main, false, &mut seq, 3000, 320, 240);
         assert_eq!(pkts.len(), 3);
 
         let mut reassembler = VideoReassembler::new();
         // Deliver out of order: 2, 0, 1
         assert!(reassembler.push(&pkts[2]).is_none()); // last arrives first — no total_fragments yet
         assert!(reassembler.push(&pkts[0]).is_none());
-        let result = reassembler.push(&pkts[1]).expect("last missing fragment completes frame");
-        assert_eq!(result.0, CodecId::Av1Main);
-        assert!(!result.1);
-        assert_eq!(result.2, frame);
+        let result = reassembler
+            .push(&pkts[1])
+            .expect("last missing fragment completes frame");
+        assert_eq!(result.codec_id, CodecId::Av1Main);
+        assert!(!result.is_keyframe);
+        assert_eq!(result.width, Some(320));
+        assert_eq!(result.height, Some(240));
+        assert_eq!(result.data, frame);
     }
 
     #[test]
     fn empty_frame_produces_no_packets() {
         let mut seq = 0u32;
-        let pkts = packetize_video_frame(&[], CodecId::Av1Main, false, &mut seq, 0);
+        let pkts = packetize_video_frame(&[], CodecId::Av1Main, false, &mut seq, 0, 640, 480);
         assert!(pkts.is_empty());
     }
+
+    #[test]
+    fn old_payload_without_meta_still_reassembles() {
+        let payload = Bytes::copy_from_slice(&[0x00, 0x00, 0x00, 0x01, 0x65]);
+        let pkt = MediaPacket {
+            header: MediaHeaderV2 {
+                version: MediaHeaderV2::VERSION,
+                flags: MediaHeaderV2::FLAG_KEYFRAME | MediaHeaderV2::FLAG_FRAME_END,
+                media_type: MediaType::Video,
+                codec_id: CodecId::H264Baseline,
+                stream_id: 0,
+                fec_ratio: 0,
+                seq: 7,
+                timestamp: 123,
+                fec_block: 1,
+            },
+            payload: payload.clone(),
+            quality_report: None,
+        };
+
+        let mut reassembler = VideoReassembler::new();
+        let frame = reassembler.push(&pkt).unwrap();
+        assert_eq!(frame.codec_id, CodecId::H264Baseline);
+        assert_eq!(frame.width, None);
+        assert_eq!(frame.height, None);
+        assert_eq!(frame.data, payload.to_vec());
+    }
 }

crates/wzp-video/tests/pipeline_roundtrip.rs

@@ -16,9 +16,9 @@
 use std::sync::Mutex;
 use wzp_proto::CodecId;
 use wzp_video::{
-    VideoFrame,
     factory::{create_video_decoder, create_video_encoder},
-    transport::{VideoReassembler, packetize_video_frame},
+    transport::{packetize_video_frame, VideoReassembler},
+    VideoFrame,
 };
 
 /// VideoToolbox has global session registry state — serialise integration tests
@@ -42,7 +42,12 @@ fn synthetic_i420(width: u32, height: u32, frame_idx: u32) -> VideoFrame {
     data[y_size..y_size + uv_size].fill(128);
     data[y_size + uv_size..].fill(128);
 
-    VideoFrame { width, height, data, timestamp_ms: frame_idx as u64 * 33 }
+    VideoFrame {
+        width,
+        height,
+        data,
+        timestamp_ms: frame_idx as u64 * 33,
+    }
 }
 
 // ── tests ─────────────────────────────────────────────────────────────────────
@@ -53,10 +58,10 @@ fn h264_pipeline_roundtrip() {
     let _g = VT_LOCK.lock().unwrap();
     let (w, h) = (640, 360);
 
-    let mut encoder = create_video_encoder(CodecId::H264Baseline, w, h, 1_500_000)
-        .expect("H264Baseline encoder");
-    let mut decoder = create_video_decoder(CodecId::H264Baseline, w, h)
-        .expect("H264Baseline decoder");
+    let mut encoder =
+        create_video_encoder(CodecId::H264Baseline, w, h, 1_500_000).expect("H264Baseline encoder");
+    let mut decoder =
+        create_video_decoder(CodecId::H264Baseline, w, h).expect("H264Baseline decoder");
 
     let mut seq = 0u32;
     let mut decoded_count = 0usize;
@@ -71,32 +76,60 @@ fn h264_pipeline_roundtrip() {
         }
 
         let is_keyframe = encoder.is_keyframe(&encoded);
-        let pkts = packetize_video_frame(&encoded, CodecId::H264Baseline, is_keyframe, &mut seq, i * 33);
-        assert!(!pkts.is_empty(), "packetize must produce at least one packet");
+        let pkts = packetize_video_frame(
+            &encoded,
+            CodecId::H264Baseline,
+            is_keyframe,
+            &mut seq,
+            i * 33,
+            w,
+            h,
+        );
+        assert!(
+            !pkts.is_empty(),
+            "packetize must produce at least one packet"
+        );
 
         // All fragments for this frame share the same timestamp.
         let ts = pkts[0].header.timestamp;
         let total_frags = pkts.len();
         for (idx, pkt) in pkts.iter().enumerate() {
-            assert_eq!(pkt.header.timestamp, ts, "all fragments of one frame share timestamp");
+            assert_eq!(
+                pkt.header.timestamp, ts,
+                "all fragments of one frame share timestamp"
+            );
             let frag_idx = (pkt.header.fec_block >> 8) as usize;
             let frag_total = (pkt.header.fec_block & 0xFF) as usize;
             assert_eq!(frag_idx, idx, "fragment index must match packet position");
-            assert_eq!(frag_total, total_frags, "all fragments carry the correct total count");
+            assert_eq!(
+                frag_total, total_frags,
+                "all fragments carry the correct total count"
+            );
         }
-        assert!(pkts.last().unwrap().header.is_frame_end(), "last packet must have FLAG_FRAME_END");
+        assert!(
+            pkts.last().unwrap().header.is_frame_end(),
+            "last packet must have FLAG_FRAME_END"
+        );
 
         // Push through reassembler — only the last packet should yield a frame.
         let mut reassembler = VideoReassembler::new();
         for (j, pkt) in pkts.iter().enumerate() {
             let result = reassembler.push(pkt);
             if j + 1 < pkts.len() {
-                assert!(result.is_none(), "intermediate fragments must not yield a complete frame");
+                assert!(
+                    result.is_none(),
+                    "intermediate fragments must not yield a complete frame"
+                );
             } else {
-                let (codec, kf, data) = result.expect("last fragment must complete the frame");
-                assert_eq!(codec, CodecId::H264Baseline);
-                assert_eq!(kf, is_keyframe);
-                assert_eq!(data, encoded, "reassembled bytes must match original encoded bytes");
+                let frame = result.expect("last fragment must complete the frame");
+                assert_eq!(frame.codec_id, CodecId::H264Baseline);
+                assert_eq!(frame.is_keyframe, is_keyframe);
+                assert_eq!(frame.width, Some(w as u16));
+                assert_eq!(frame.height, Some(h as u16));
+                assert_eq!(
+                    frame.data, encoded,
+                    "reassembled bytes must match original encoded bytes"
+                );
             }
         }
 
@@ -118,7 +151,10 @@ fn h264_pipeline_roundtrip() {
         }
     }
 
-    assert!(decoded_count > 0, "at least one frame must have been decoded");
+    assert!(
+        decoded_count > 0,
+        "at least one frame must have been decoded"
+    );
 }
 
 /// Fragmentation: a frame larger than VIDEO_MAX_PAYLOAD splits into multiple packets,
@@ -134,13 +170,28 @@ fn large_frame_fragments_and_reassembles() {
 
     let mut seq = 0u32;
     let pkts = packetize_video_frame(
-        &synthetic_encoded, CodecId::H264Baseline, true, &mut seq, 9000,
+        &synthetic_encoded,
+        CodecId::H264Baseline,
+        true,
+        &mut seq,
+        9000,
+        1280,
+        720,
     );
 
     assert!(pkts.len() >= 4, "large frame must produce ≥4 fragments");
-    assert!(pkts[0].header.is_keyframe(), "keyframe flag propagates to all fragments");
-    assert!(!pkts[0].header.is_frame_end(), "first packet is not frame end");
-    assert!(pkts.last().unwrap().header.is_frame_end(), "last packet is frame end");
+    assert!(
+        pkts[0].header.is_keyframe(),
+        "keyframe flag propagates to all fragments"
+    );
+    assert!(
+        !pkts[0].header.is_frame_end(),
+        "first packet is not frame end"
+    );
+    assert!(
+        pkts.last().unwrap().header.is_frame_end(),
+        "last packet is frame end"
+    );
 
     let mut reassembler = VideoReassembler::new();
     let mut result = None;
@@ -148,8 +199,13 @@ fn large_frame_fragments_and_reassembles() {
         result = reassembler.push(pkt);
     }
 
-    let (_, _, data) = result.expect("all fragments delivered → complete frame");
-    assert_eq!(data, synthetic_encoded, "reassembled bytes must match input exactly");
+    let frame = result.expect("all fragments delivered → complete frame");
+    assert_eq!(frame.width, Some(1280));
+    assert_eq!(frame.height, Some(720));
+    assert_eq!(
+        frame.data, synthetic_encoded,
+        "reassembled bytes must match input exactly"
+    );
 }
 
 /// Packet loss: if the first fragment is missing, reassembly cannot complete.
@@ -159,7 +215,7 @@ fn missing_fragment_blocks_reassembly() {
 
     let frame: Vec<u8> = vec![0xAB; VIDEO_MAX_PAYLOAD * 2 + 50];
     let mut seq = 0u32;
-    let pkts = packetize_video_frame(&frame, CodecId::Av1Main, false, &mut seq, 1234);
+    let pkts = packetize_video_frame(&frame, CodecId::Av1Main, false, &mut seq, 1234, 640, 480);
     assert!(pkts.len() >= 3);
 
     let mut reassembler = VideoReassembler::new();
@@ -193,7 +249,15 @@ fn evict_stale_removes_aged_frames() {
 
     let frame: Vec<u8> = vec![0x55; VIDEO_MAX_PAYLOAD * 2];
     let mut seq = 0u32;
-    let pkts = packetize_video_frame(&frame, CodecId::H264Baseline, false, &mut seq, 500);
+    let pkts = packetize_video_frame(
+        &frame,
+        CodecId::H264Baseline,
+        false,
+        &mut seq,
+        500,
+        640,
+        480,
+    );
 
     let mut reassembler = VideoReassembler::new();
     // Push only first packet — frame is incomplete.

desktop/src-tauri/src/engine.rs

@@ -1385,7 +1385,7 @@ impl CallEngine {
             // Video pipeline state — mirror of the desktop recv task.
             let mut video_reassembler = wzp_video::transport::VideoReassembler::new();
             let mut video_decoder: Option<Box<dyn wzp_video::decoder::VideoDecoder>> = None;
-            let mut video_decoder_codec: Option<wzp_proto::CodecId> = None;
+            let mut video_decoder_key: Option<(wzp_proto::CodecId, u32, u32)> = None;
             let mut video_first_recv_logged = false;
             let mut video_first_reassembled_logged = false;
             let mut video_reassembled_samples: u64 = 0;
@@ -1466,7 +1466,14 @@ impl CallEngine {
                                     }),
                                 );
                             }
-                            if let Some((codec_id, is_kf, frame)) = video_reassembler.push(&pkt) {
+                            if let Some(reassembled) = video_reassembler.push(&pkt) {
+                                let codec_id = reassembled.codec_id;
+                                let is_kf = reassembled.is_keyframe;
+                                let frame_width =
+                                    reassembled.width.unwrap_or(video_width as u16) as u32;
+                                let frame_height =
+                                    reassembled.height.unwrap_or(video_height as u16) as u32;
+                                let frame = reassembled.data;
                                 video_reassembled_samples += 1;
                                 if !video_first_reassembled_logged {
                                     video_first_reassembled_logged = true;
@@ -1484,6 +1491,14 @@ impl CallEngine {
                                     );
                                 }
                                 if should_log_video_sample(video_reassembled_samples, is_kf) {
+                                    crate::maybe_dump_video_bytes(
+                                        &recv_app,
+                                        "remote_encoded_reassembled",
+                                        "android",
+                                        video_reassembled_samples,
+                                        &frame,
+                                        codec_id,
+                                    );
                                     crate::emit_call_debug(
                                         &recv_app,
                                         "video:reassembled_frame",
@@ -1517,22 +1532,23 @@ impl CallEngine {
                                     video_reassembler.evict_stale(pkt.header.timestamp, 5_000);
                                     continue;
                                 }
-                                if video_decoder_codec != Some(codec_id) {
+                                let decoder_key = (codec_id, frame_width, frame_height);
+                                if video_decoder_key != Some(decoder_key) {
                                     crate::emit_call_debug(
                                         &recv_app,
                                         "video:decoder_init_start",
                                         serde_json::json!({
                                             "t_ms": recv_t0.elapsed().as_millis() as u64,
                                             "codec": format!("{:?}", codec_id),
-                                            "width": video_width,
-                                            "height": video_height,
+                                            "width": frame_width,
+                                            "height": frame_height,
                                             "platform": "android",
                                         }),
                                     );
                                     match wzp_video::factory::create_video_decoder(
                                         codec_id,
-                                        video_width,
-                                        video_height,
+                                        frame_width,
+                                        frame_height,
                                     ) {
                                         Ok(d) => {
                                             info!(codec = ?codec_id, "video decoder created (android)");
@@ -1546,7 +1562,7 @@ impl CallEngine {
                                                 }),
                                             );
                                             video_decoder = Some(d);
-                                            video_decoder_codec = Some(codec_id);
+                                            video_decoder_key = Some(decoder_key);
                                         }
                                         Err(e) => {
                                             error!("video decoder init failed: {e}");
@@ -2304,11 +2320,21 @@ impl CallEngine {
                         is_keyframe,
                         &mut seq,
                         ts_ms,
+                        frame.width,
+                        frame.height,
                     );
                     video_packets_total += pkts.len() as u64;
                     video_bytes_total += encoded.len() as u64;
                     if encoded_frame_samples < 5 {
                         encoded_frame_samples += 1;
+                        crate::maybe_dump_video_bytes(
+                            &vid_app,
+                            "local_encoded",
+                            "android",
+                            encoded_frame_samples,
+                            &encoded,
+                            vid_codec,
+                        );
                         let packet_payload_bytes: usize =
                             pkts.iter().map(|pkt| pkt.payload.len()).sum();
                         crate::emit_call_debug(
@@ -2870,7 +2896,7 @@ impl CallEngine {
             let mut first_packet_logged = false;
             let mut video_reassembler = wzp_video::transport::VideoReassembler::new();
             let mut video_decoder: Option<Box<dyn wzp_video::decoder::VideoDecoder>> = None;
-            let mut video_decoder_codec: Option<wzp_proto::CodecId> = None;
+            let mut video_decoder_key: Option<(wzp_proto::CodecId, u32, u32)> = None;
             let mut video_first_recv_logged_desktop = false;
             let mut video_first_reassembled_logged = false;
             let mut video_reassembled_samples: u64 = 0;
@@ -2956,7 +2982,14 @@ impl CallEngine {
                                     }),
                                 );
                             }
-                            if let Some((codec_id, is_kf, frame)) = video_reassembler.push(&pkt) {
+                            if let Some(reassembled) = video_reassembler.push(&pkt) {
+                                let codec_id = reassembled.codec_id;
+                                let is_kf = reassembled.is_keyframe;
+                                let frame_width =
+                                    reassembled.width.unwrap_or(video_width as u16) as u32;
+                                let frame_height =
+                                    reassembled.height.unwrap_or(video_height as u16) as u32;
+                                let frame = reassembled.data;
                                 video_reassembled_samples += 1;
                                 if !video_first_reassembled_logged {
                                     video_first_reassembled_logged = true;
@@ -2974,6 +3007,14 @@ impl CallEngine {
                                     );
                                 }
                                 if should_log_video_sample(video_reassembled_samples, is_kf) {
+                                    crate::maybe_dump_video_bytes(
+                                        &recv_app,
+                                        "remote_encoded_reassembled",
+                                        "desktop",
+                                        video_reassembled_samples,
+                                        &frame,
+                                        codec_id,
+                                    );
                                     crate::emit_call_debug(
                                         &recv_app,
                                         "video:reassembled_frame",
@@ -3008,22 +3049,23 @@ impl CallEngine {
                                     continue;
                                 }
                                 // Lazy-init or switch decoder on codec change.
-                                if video_decoder_codec != Some(codec_id) {
+                                let decoder_key = (codec_id, frame_width, frame_height);
+                                if video_decoder_key != Some(decoder_key) {
                                     crate::emit_call_debug(
                                         &recv_app,
                                         "video:decoder_init_start",
                                         serde_json::json!({
                                             "t_ms": recv_t0.elapsed().as_millis() as u64,
                                             "codec": format!("{:?}", codec_id),
-                                            "width": video_width,
-                                            "height": video_height,
+                                            "width": frame_width,
+                                            "height": frame_height,
                                             "platform": "desktop",
                                         }),
                                     );
                                     match wzp_video::factory::create_video_decoder(
                                         codec_id,
-                                        video_width,
-                                        video_height,
+                                        frame_width,
+                                        frame_height,
                                     ) {
                                         Ok(d) => {
                                             info!(codec = ?codec_id, "video decoder created");
@@ -3037,7 +3079,7 @@ impl CallEngine {
                                                 }),
                                             );
                                             video_decoder = Some(d);
-                                            video_decoder_codec = Some(codec_id);
+                                            video_decoder_key = Some(decoder_key);
                                         }
                                         Err(e) => {
                                             error!("video decoder init failed: {e}");
@@ -3640,11 +3682,21 @@ impl CallEngine {
                         is_keyframe,
                         &mut seq,
                         ts_ms,
+                        frame.width,
+                        frame.height,
                     );
                     video_packets_total += pkts.len() as u64;
                     video_bytes_total += encoded.len() as u64;
                     if encoded_frame_samples < 5 {
                         encoded_frame_samples += 1;
+                        crate::maybe_dump_video_bytes(
+                            &vid_app,
+                            "local_encoded",
+                            "desktop",
+                            encoded_frame_samples,
+                            &encoded,
+                            vid_codec,
+                        );
                         let packet_payload_bytes: usize =
                             pkts.iter().map(|pkt| pkt.payload.len()).sum();
                         crate::emit_call_debug(

desktop/src-tauri/src/lib.rs

@@ -205,6 +205,61 @@ pub(crate) fn maybe_dump_video_jpeg(
     }
 }
 
+pub(crate) fn maybe_dump_video_bytes(
+    app: &tauri::AppHandle,
+    stage: &str,
+    platform: &str,
+    frame_no: u64,
+    bytes: &[u8],
+    codec: wzp_proto::CodecId,
+) {
+    if !should_dump_frame(frame_no) || bytes.is_empty() {
+        return;
+    }
+
+    let ext = match codec {
+        wzp_proto::CodecId::H265Main => "h265",
+        wzp_proto::CodecId::Av1Main => "obu",
+        _ => "h264",
+    };
+    let seq = FRAME_DUMP_WRITES.fetch_add(1, Ordering::Relaxed) + 1;
+    let dir = identity_dir().join("frame-dumps");
+    let file_name = format!("{seq:06}_{platform}_{stage}_f{frame_no:06}.{ext}");
+    let path = dir.join(file_name);
+    let result = std::fs::create_dir_all(&dir).and_then(|_| std::fs::write(&path, bytes));
+
+    match result {
+        Ok(()) => emit_call_debug(
+            app,
+            "video:byte_dump",
+            serde_json::json!({
+                "stage": stage,
+                "platform": platform,
+                "frame_no": frame_no,
+                "codec": format!("{:?}", codec),
+                "bytes": bytes.len(),
+                "path": path,
+            }),
+        ),
+        Err(e) => {
+            if seq <= 5 || seq % 30 == 0 {
+                emit_call_debug(
+                    app,
+                    "video:byte_dump_failed",
+                    serde_json::json!({
+                        "stage": stage,
+                        "platform": platform,
+                        "frame_no": frame_no,
+                        "codec": format!("{:?}", codec),
+                        "error": e.to_string(),
+                        "path": path,
+                    }),
+                );
+            }
+        }
+    }
+}
+
 /// RGB24 → I420 (planar 4:2:0).  Layout: Y(w×h) | U(w/2×h/2) | V(w/2×h/2).
 fn rgb_to_i420(rgb: &[u8], w: usize, h: usize) -> Vec<u8> {
     let y_size = w * h;

desktop/src/main.ts

@@ -607,7 +607,7 @@ function drawCameraFrameForSend() {
   const vh = vdLocalVideo.videoHeight || camCaptureCanvas.height;
   if (!vw || !vh) return;
 
-  const scale = Math.max(cameraSendWidth / vw, cameraSendHeight / vh);
+  const scale = Math.min(cameraSendWidth / vw, cameraSendHeight / vh);
   const dw = vw * scale;
   const dh = vh * scale;
   const dx = (cameraSendWidth - dw) / 2;
@@ -631,6 +631,8 @@ async function captureAndPushCameraFrame() {
         frame_no: cameraCaptureFrameNo,
         width: camCaptureCanvas.width,
         height: camCaptureCanvas.height,
+        source_width: vdLocalVideo.videoWidth || null,
+        source_height: vdLocalVideo.videoHeight || null,
         jpeg_b64_len: b64.length,
         capture_clock: getVideoFrameCallbackApi() ? "video_frame_callback" : "interval",
       });