feat(assets): SA3 音效补齐 radio 11+1 与 dungeon 13源+15pan（token 走 hf-mirror 实测可用）

- 模型 17/17 文件经镜像全量缓存（gated+token，直连本机不通；sfx.md/setup.md/asset-pipeline.md 镜像结论同步更新）
- 修复迁移遗留：stable_audio_3/models/ 源码子包被 .gitignore models/ 规则误伤丢失，从上游恢复并加白名单
- radio：arg_muffled/brake_screech 等叙事件落地（接线原有 L111/L154 零改动）+ phone_ring SYN→SA3 升级；dungeon 13 源 A/B 对齐（RMS 偏差 ≤0.3dB）全量同名替换，SYN 原版备份 tools/asset_fix_backup/sa3_ab_20260902/
- 关键玩法语义达标：echo 距离档 0.83<1.43<2.18<2.98s 严格递增；one-shot 真峰值全 ≤-3dBFS（解码回读法）
- check_all_assets 8 游戏全绿（radio 254/254、dungeon 303/303）；playtest radio 221/dungeon 1610 全绿

tools/stable-audio-3/stable_audio_3/models/pretransforms.py

@@ -0,0 +1,84 @@
+import torch
+import torch.nn as nn
+from einops import rearrange
+from torchaudio.transforms import Resample
+from .blocks import ResidualUnit, WNConv1d
+
+
+class AutoencoderPretransform(nn.Module):
+    def __init__(self, model, scale=1.0, iterate_batch=False, chunked=False):
+        super().__init__()
+        self.model = model
+        self.model.requires_grad_(False).eval()
+        self.scale = scale
+        self.downsampling_ratio = model.downsampling_ratio
+        self.io_channels = model.io_channels
+        self.enable_grad = False
+        self.iterate_batch = iterate_batch
+        self.chunked = chunked
+
+    def encode(self, x, **kwargs):
+        return self.model.encode_audio(x, chunked=self.chunked, iterate_batch=self.iterate_batch, **kwargs) / self.scale
+
+    def decode(self, z, chunked=None, **kwargs):
+        chunked = self.chunked if chunked is None else chunked
+        return self.model.decode_audio(z * self.scale, chunked=chunked, iterate_batch=self.iterate_batch, **kwargs)
+
+def fold_channels_into_batch(x):
+    x = rearrange(x, 'b c ... -> (b c) ...')
+    return x
+
+def unfold_channels_from_batch(x, channels):
+    if channels == 1:
+        return x.unsqueeze(1)
+    x = rearrange(x, '(b c) ... -> b c ...', c = channels)
+    return x
+
+
+class PatchedPretransform(nn.Module):
+    def __init__(self, channels, patch_size, oversampling = 1, postfilter_channels = 0, **kwargs):
+        super().__init__()
+        self.channels = channels
+        self.patch_size = patch_size
+        self.oversampling = oversampling
+
+        self.downsampling_ratio = patch_size
+        self.io_channels = channels
+        self.encoded_channels = channels * patch_size
+        self.enable_grad = False
+
+        if self.oversampling > 1:
+            self.input_upsampler = Resample(1, self.oversampling)
+            self.output_downsampler = Resample(self.oversampling, 1)
+
+        if postfilter_channels > 0:
+            self.postfilter = nn.Sequential(
+            WNConv1d(in_channels=channels, out_channels=postfilter_channels, kernel_size=7, padding=3, bias=True),
+            ResidualUnit(in_channels=postfilter_channels, out_channels=postfilter_channels,
+                         dilation=1, use_snake=True, bias = True),
+            ResidualUnit(in_channels=postfilter_channels, out_channels=postfilter_channels,
+                         dilation=3, use_snake=True, bias = True),
+            ResidualUnit(in_channels=postfilter_channels, out_channels=postfilter_channels,
+                         dilation=9, use_snake=True, bias = True),
+            WNConv1d(in_channels=postfilter_channels, out_channels=channels, kernel_size=7, padding=3, bias=False))
+
+    def _pad(self, x):
+        seq_len = x.shape[-1]
+        pad_len = (self.patch_size - (seq_len % self.patch_size)) % self.patch_size
+        if pad_len > 0:
+            x = torch.cat([x, torch.zeros_like(x[:, :, :pad_len])], dim=-1)
+        return x
+        
+    def encode(self, x):
+        if self.oversampling > 1:
+            x = self.input_upsampler(x)
+        x = self._pad(x)
+        x = rearrange(x, "b c (l h) -> b (c h) l", h=self.patch_size)
+        return x
+    def decode(self, x):
+        x = rearrange(x, "b (c h) l -> b c (l h)", h=self.patch_size)
+        if hasattr(self, 'postfilter'):
+            x = self.postfilter(x)
+        if self.oversampling > 1:
+            x = self.output_downsampler(x)
+        return x