fix(unified-render): 无音轨视频防御 + probe_has_audio 工具

- 新增 ffmpeg_utils.probe_has_audio：ffprobe 探测音频流
- _mix_audio 入口过滤无音频流的 clip，避免 FFmpeg 引用 [i:a] 失败
- 新增 _clip_has_audio 缓存方法，同 clip 只探测一次
- 6个新增单测覆盖：全无音频、部分无音频、主图层无但独立音轨有、缓存、双无音频兜底

apps/worker/video_processing/ffmpeg_utils.py

@@ -85,6 +85,41 @@ def run_ffmpeg(
         raise
 
 
+def probe_has_audio(local_path: str | Path) -> bool:
+    """探测文件是否包含音频流。
+
+    Args:
+        local_path: 本地文件路径
+
+    Returns:
+        True 表示有音频流（或探测失败保守返回），False 表示确认无音频流
+    """
+    try:
+        result = subprocess.run(  # nosec B603
+            [
+                FFPROBE_BIN,
+                "-v",
+                "error",
+                "-select_streams",
+                "a:0",
+                "-show_entries",
+                "stream=codec_type",
+                "-of",
+                "default=noprint_wrappers=1:nokey=1",
+                str(local_path),
+            ],
+            check=True,
+            stdout=subprocess.PIPE,
+            stderr=subprocess.PIPE,
+            text=True,
+            timeout=10,
+        )
+        return result.stdout.strip() == "audio"
+    except Exception:
+        # 探测失败保守返回 True，让 FFmpeg 自己处理（避免误删音频）
+        return True
+
+
 def probe_duration(local_path: str | Path) -> float:
     """用 ffprobe 获取视频时长（秒）。
 

apps/worker/video_processing/unified_render_service.py

@@ -1036,6 +1036,7 @@ class UnifiedRenderService:
         2. 主图层音频按顺序 concat 拼接
         3. 独立音频轨（audio role）用 amix 混入
         4. 输出时长截断到 video_duration
+        5. 无音频流的 clip 会被自动跳过，避免 FFmpeg 引用 [i:a] 失败
 
         Args:
             layers: 图层列表
@@ -1067,6 +1068,11 @@ class UnifiedRenderService:
         if "audio" in layer_map:
             audio_clips = layer_map["audio"].clips
 
+        # ── 防御：过滤掉无音频流的 clip ──
+        # 源视频可能没有音频流（如静音视频、纯图片转的视频），直接引用 [i:a] 会导致 FFmpeg 失败
+        main_clips = [c for c in main_clips if self._clip_has_audio(c)]
+        audio_clips = [c for c in audio_clips if self._clip_has_audio(c)]
+
         if not main_clips and not audio_clips:
             return None
 
@@ -1306,3 +1312,17 @@ class UnifiedRenderService:
         if clip.duration > 0:
             return min(clip.duration, clip.actual_duration) if clip.actual_duration > 0 else clip.duration
         return clip.actual_duration if clip.actual_duration > 0 else 0.0
+
+    def _clip_has_audio(self, clip: ResolvedClip) -> bool:
+        """探测 clip 是否有音频流（带缓存）.
+
+        避免同一个 clip 被多次 ffprobe 探测。
+        """
+        if not hasattr(self, "_audio_cache"):
+            self._audio_cache: dict[str, bool] = {}
+        key = str(clip.local_path)
+        if key not in self._audio_cache:
+            from .ffmpeg_utils import probe_has_audio
+
+            self._audio_cache[key] = probe_has_audio(clip.local_path)
+        return self._audio_cache[key]

tests/unit/test_unified_render_service.py

@@ -1255,3 +1255,147 @@ class TestAudioMixing:
         mock_run.assert_called_once()
         cmd = mock_run.call_args[0][0]
         assert "aac" not in cmd  # 没有音频编码参数
+
+    # ── 无音轨视频防御测试 ──
+
+    def test_mix_audio_main_no_audio_stream_returns_none(self):
+        """主图层clip无音频流且无独立音频轨时，返回None（不报错）。"""
+        clips = [_make_clip("c1", "main", order=0, duration=5.0)]
+        asset_paths = {"asset_c1.mp4": Path("/tmp/asset_c1.mp4")}
+        svc = _make_service(clips, asset_paths)
+
+        with (
+            _patch_path_exists(),
+            patch("video_processing.unified_render_service.probe_duration", return_value=5.0),
+            patch("video_processing.ffmpeg_utils.probe_has_audio", return_value=False),
+            patch("video_processing.unified_render_service.run_ffmpeg") as mock_run,
+        ):
+            layers = svc._group_clips_into_layers(svc._resolve_clips())
+            result = svc._mix_audio(layers, 5.0)
+
+        assert result is None
+        # 没有音频流时不应调用 FFmpeg
+        mock_run.assert_not_called()
+
+    def test_mix_audio_partial_clips_no_audio_filtered(self):
+        """部分主图层clip无音频流时，过滤掉无音轨的，剩余有音频的正常concat。"""
+        clips = [
+            _make_clip("c1", "main", order=0, duration=3.0),  # 无音频
+            _make_clip("c2", "main", order=1, duration=2.0),  # 有音频
+        ]
+        asset_paths = {
+            "asset_c1.mp4": Path("/tmp/asset_c1.mp4"),
+            "asset_c2.mp4": Path("/tmp/asset_c2.mp4"),
+        }
+        svc = _make_service(clips, asset_paths)
+
+        # 模拟：c1 无音频，c2 有音频
+        def fake_has_audio(path):
+            return "c2" in str(path)
+
+        with (
+            _patch_path_exists(),
+            patch("video_processing.unified_render_service.probe_duration", return_value=5.0),
+            patch("video_processing.ffmpeg_utils.probe_has_audio", side_effect=fake_has_audio),
+            patch("video_processing.unified_render_service.run_ffmpeg") as mock_run,
+        ):
+            layers = svc._group_clips_into_layers(svc._resolve_clips())
+            result = svc._mix_audio(layers, 5.0)
+
+        assert result is not None
+        mock_run.assert_called_once()
+        cmd = mock_run.call_args[0][0]
+        cmd_str = " ".join(cmd)
+        # 只剩 1 个有效音频 clip，走单clip路径（-vn），不走 filter_complex concat
+        assert "-vn" in cmd
+        assert "concat=n=2" not in cmd_str
+
+    def test_mix_audio_all_main_no_audio_but_independent_track(self):
+        """主图层全部无音频，但有独立音频轨时，正常走amix混音。"""
+        clips = [
+            _make_clip("c1", "main", order=0, duration=5.0),  # 无音频
+            _make_clip(
+                "bgm1",
+                "main",
+                order=0,
+                duration=5.0,
+                config={"role": "audio", "volume": 0.5},
+            ),  # 独立音频轨（有音频）
+        ]
+        asset_paths = {
+            "asset_c1.mp4": Path("/tmp/asset_c1.mp4"),
+            "asset_bgm1.mp4": Path("/tmp/asset_bgm1.mp4"),
+        }
+        svc = _make_service(clips, asset_paths)
+
+        def fake_has_audio(path):
+            return "bgm" in str(path)
+
+        with (
+            _patch_path_exists(),
+            patch("video_processing.unified_render_service.probe_duration", return_value=5.0),
+            patch("video_processing.ffmpeg_utils.probe_has_audio", side_effect=fake_has_audio),
+            patch("video_processing.unified_render_service.run_ffmpeg") as mock_run,
+        ):
+            layers = svc._group_clips_into_layers(svc._resolve_clips())
+            result = svc._mix_audio(layers, 5.0)
+
+        assert result is not None
+        mock_run.assert_called_once()
+        cmd = mock_run.call_args[0][0]
+        cmd_str = " ".join(cmd)
+        # 只有独立音频轨参与混音，amix 输入数=1
+        assert "amix=inputs=1" in cmd_str
+
+    def test_mix_audio_both_no_audio_returns_none(self):
+        """主图层和独立音频轨都无音频时，返回None。"""
+        clips = [
+            _make_clip("c1", "main", order=0, duration=5.0),
+            _make_clip(
+                "bgm1",
+                "main",
+                order=0,
+                duration=5.0,
+                config={"role": "audio"},
+            ),
+        ]
+        asset_paths = {
+            "asset_c1.mp4": Path("/tmp/asset_c1.mp4"),
+            "asset_bgm1.mp4": Path("/tmp/asset_bgm1.mp4"),
+        }
+        svc = _make_service(clips, asset_paths)
+
+        with (
+            _patch_path_exists(),
+            patch("video_processing.unified_render_service.probe_duration", return_value=5.0),
+            patch("video_processing.ffmpeg_utils.probe_has_audio", return_value=False),
+            patch("video_processing.unified_render_service.run_ffmpeg") as mock_run,
+        ):
+            layers = svc._group_clips_into_layers(svc._resolve_clips())
+            result = svc._mix_audio(layers, 5.0)
+
+        assert result is None
+        mock_run.assert_not_called()
+
+    def test_clip_has_audio_cache(self):
+        """_clip_has_audio 带缓存，同一clip只探测一次。"""
+        clips = [_make_clip("c1", "main", order=0, duration=5.0)]
+        asset_paths = {"asset_c1.mp4": Path("/tmp/asset_c1.mp4")}
+        svc = _make_service(clips, asset_paths)
+
+        with (
+            _patch_path_exists(),
+            patch("video_processing.unified_render_service.probe_duration", return_value=5.0),
+        ):
+            resolved = svc._resolve_clips()
+            clip = resolved[0]
+
+        with patch("video_processing.ffmpeg_utils.probe_has_audio", return_value=True) as mock_probe:
+            # 调用 3 次
+            r1 = svc._clip_has_audio(clip)
+            r2 = svc._clip_has_audio(clip)
+            r3 = svc._clip_has_audio(clip)
+
+        assert r1 is True and r2 is True and r3 is True
+        # 实际只探测了 1 次
+        assert mock_probe.call_count == 1