render: fix 4K playback memory growth and decode-to-target-size

Root causes found for the 4K stalls and the second-footage memory
blowup (audit + code review):

- ticket bookkeeping leaked unbounded: the procpool ticket table and
  the arena slot map only ever grew (50-100 tickets/sec during
  playback, each pinning montage params and shm region views).
  Completed/cancelled/superseded/crashed entries are now removed, and
  the arena reaps fire-and-forget tickets once finished; the sync poll
  path reaps via a terminal result() read. InFlight duplicate submits
  now answer State immediately instead of sitting in the map forever.
- decode ran a full-resolution swscale to F32 RGBA (~132 MB at 4K)
  plus a second full-res copy before downscaling to the 480px proxy:
  RetrieveVideoParams.target_size lets swscale convert AND resize in
  one pass (bilinear, matching the old Rust resampler), so a 4K
  preview frame costs ~1 MB instead of ~260 MB of churn. This applies
  to proxy AND full-res requests alike.
- per-process decoder cache was unbounded (each session pins an FFmpeg
  context + 2 native decoded frames): LRU-capped at 16, eviction drops
  the map entry (in-flight renders keep their Arc; Drop releases
  FFmpeg).
- playback window completions were not generation-gated: a stale
  render from before an edit landed in the rebuilt window (wrong frame
  displayed, fresh request blocked). Stale completions now return
  their shm slot credit instead.
- async audio prefetch used the polling ticket submit without ever
  polling: switched to the fire-and-forget submit so entries reap.

crates/oak-codec/src/decoder.rs

@@ -136,6 +136,13 @@ pub struct RetrieveVideoParams {
 	pub mode: RenderMode,
 	/// Frame alpha channel is premultiplied.
 	pub alpha_is_premultiplied: bool,
+	/// Target output size for the scaled frame: `Some((w, h))` lets the
+	/// decoder's swscale pass convert AND resize in one step (native
+	/// yuv → RGBA/F32 at the target size), skipping the full-resolution
+	/// float intermediate (a 4K frame is ~132 MB as F32 RGBA — decoding
+	/// to a 480px preview through it costs ~260 MB of churn per frame).
+	/// `None` keeps the native size (the old behavior).
+	pub target_size: Option<(u32, u32)>,
 }
 
 /// `Decoder::RetrieveAudioStatus` — outcome of an audio retrieve.
@@ -708,6 +715,7 @@ mod tests_unimplemented {
 			image_sequence_number: 0,
 			mode: RenderMode::Offline,
 			alpha_is_premultiplied: false,
+			target_size: None,
 		};
 		assert!(d.retrieve_video_frame(&p).is_err());
 		assert!(d.retrieve_video(&p).is_err());

crates/oak-codec/src/ffmpeg.rs

@@ -332,7 +332,7 @@ impl Decoder for FFmpegDecoder {
 		let f = decoded?
 			.ok_or_else(|| fail("no video frame available at the requested time"))?;
 
-		let (w, h, bytes) = state.scale_video_to_f32(f, p.force_range)?;
+		let (w, h, bytes) = state.scale_video_to_f32(f, p.force_range, p.target_size)?;
 		let frame = copy_rgba_f32_to_frame(w, h, &bytes, p.time)?;
 		Ok(Arc::new(frame))
 	}
@@ -908,10 +908,15 @@ impl DecoderState {
 	/// Scale a decoded frame to float RGBA (F32, 4 channels), returning the
 	/// raw pixel bytes plus dimensions. Mirrors `pre_process_frame` +
 	/// `retrieve_video_frame_internal` scaling with the color-range forcing.
+	/// `target_size` resizes in the same swscale pass (native → RGBA/F32 at
+	/// the target size) instead of converting at native size first — the
+	/// caller's downscale then degenerates to a plain copy, and no
+	/// full-resolution float intermediate (~132 MB at 4K) ever exists.
 	fn scale_video_to_f32(
 		&mut self,
 		f: ffmpeg::frame::Video,
 		force_range: i32,
+		target_size: Option<(u32, u32)>,
 	) -> crate::error::Result<(u32, u32, Vec<u8>)> {
 		let video = self
 			.video
@@ -929,7 +934,12 @@ impl DecoderState {
 			ffmpeg::color::Range::MPEG
 		});
 
-		let (w, h) = (f.width(), f.height());
+		let (src_w, src_h) = (f.width(), f.height());
+		// 目标尺寸（None = 原生；0 边回退原生，swscale 不接受 0）。
+		let (w, h) = match target_size {
+			Some((tw, th)) if tw > 0 && th > 0 => (tw, th),
+			_ => (src_w, src_h),
+		};
 
 		// swscale cannot reliably output float RGBA on every build:
 		// float output is missing from some static FFmpeg swscale
@@ -945,7 +955,7 @@ impl DecoderState {
 		} else {
 			(Pixel::RGBA, false)
 		};
-		let ctx = get_or_create_scaler(&mut video.scaler, src_format, w, h, out_fmt, w, h)?;
+		let ctx = get_or_create_scaler(&mut video.scaler, src_format, src_w, src_h, out_fmt, w, h)?;
 		let mut out = ffmpeg::frame::Video::empty();
 		ctx.run(&f, &mut out).map_err(ffmpeg_err)?;
 		let stride = out.stride(0);
@@ -1389,6 +1399,8 @@ fn get_or_create_scaler(
 		None => true,
 	};
 	if recreate {
+		// BILINEAR：与渲染侧原 Rust 双线性重采样器等效（POINT 会
+		// 明显锯齿）；同尺寸纯格式转换时滤波器不参与运算。
 		let ctx = scaling::Context::get(
 			src_format,
 			src_width,
@@ -1396,7 +1408,7 @@ fn get_or_create_scaler(
 			dst_format,
 			dst_width,
 			dst_height,
-			scaling::Flags::POINT,
+			scaling::Flags::BILINEAR,
 		)
 		.map_err(ffmpeg_err)?;
 		*cache = Some(ScalingCache {
@@ -2448,6 +2460,7 @@ mod tests {
 			image_sequence_number: 0,
 			mode: crate::decoder::RenderMode::Offline,
 			alpha_is_premultiplied: false,
+			target_size: None,
 		}
 	}
 

crates/oak-codec/src/oiio.rs

@@ -242,6 +242,7 @@ mod tests {
 			image_sequence_number: 0,
 			mode: crate::decoder::RenderMode::Offline,
 			alpha_is_premultiplied: false,
+			target_size: None,
 		}
 	}
 

crates/oak-codec/src/realmedia_tests.rs

@@ -54,6 +54,7 @@ fn video_params(stream: CodecStream, time: Rational) -> RetrieveVideoParams {
 		image_sequence_number: 0,
 		mode: RenderMode::Offline,
 		alpha_is_premultiplied: false,
+		target_size: None,
 	}
 }