apps/api/app/api/routes/ai_avatar_render.py

@@ -321,4 +321,4 @@ def finalize_render_job(
         ) from exc
     except Exception as exc:
         logger.error("渲染任务finalize失败: job_id=%s err=%s", job_id, exc, exc_info=True)
-        raise HTTPException(status_code=500, detail=f"保存到成片库失败: {str(exc)}")
+        raise HTTPException(status_code=500, detail=f"保存到成片库失败: {str(exc)}") from exc

apps/api/app/schemas/lipsync.py

@@ -82,8 +82,9 @@ class CreateLipsyncJobRequest(BaseModel):
         if not video.startswith(("http://", "https://")):
             raise ValueError("video_url 必须是 HTTP/HTTPS URL")
         lower = video.lower().split("?")[0]
-        if not lower.endswith(".mp4"):
-            raise ValueError("video_url 仅支持 MP4 格式")
+        allowed_video_exts = (".mp4", ".mov", ".m4v", ".webm", ".avi", ".mkv", ".3gp")
+        if not any(lower.endswith(ext) for ext in allowed_video_exts):
+            raise ValueError("video_url 格式不支持，仅支持: " + ", ".join(allowed_video_exts))
 
         has_audio = bool((self.audio_url or "").strip())
         has_tts = bool((self.voice_id or "").strip()) and bool((self.script_text or "").strip())

tests/unit/test_ai_avatar_emotion_tts_lipsync.py

@@ -262,8 +262,8 @@ def test_smart_cover_selects_best_frame_and_persists():
     score_patch.assert_called_once()
     # 验证使用了增大的轮询参数
     call_kwargs = mk.extract_frames.call_args
-    assert call_kwargs.kwargs.get("poll_interval") == 1.0 or call_kwargs[1].get("poll_interval") == 1.0
-    assert call_kwargs.kwargs.get("max_poll_attempts") == 15 or call_kwargs[1].get("max_poll_attempts") == 15
+    assert call_kwargs.kwargs.get("poll_interval") == 2.0 or call_kwargs[1].get("poll_interval") == 2.0
+    assert call_kwargs.kwargs.get("max_poll_attempts") == 30 or call_kwargs[1].get("max_poll_attempts") == 30
 
 
 def test_smart_cover_returns_empty_when_mediakit_unavailable():
@@ -334,8 +334,8 @@ def test_extract_frames_uses_extended_poll_params():
         cov.select_best_cover_frame("https://other/avatar.mp4", max_frames=3)
 
     call_kwargs = mk.extract_frames.call_args
-    assert call_kwargs.kwargs.get("poll_interval") == 1.0 or call_kwargs[1].get("poll_interval") == 1.0
-    assert call_kwargs.kwargs.get("max_poll_attempts") == 15 or call_kwargs[1].get("max_poll_attempts") == 15
+    assert call_kwargs.kwargs.get("poll_interval") == 2.0 or call_kwargs[1].get("poll_interval") == 2.0
+    assert call_kwargs.kwargs.get("max_poll_attempts") == 30 or call_kwargs[1].get("max_poll_attempts") == 30
     assert call_kwargs.kwargs.get("max_retries") == 1 or call_kwargs[1].get("max_retries") == 1
 
 

tests/unit/test_lipsync_routes.py

@@ -91,16 +91,27 @@ class TestSchemaValidation:
         assert req.voice_id == "longxiaochun_v3"
         assert req.script_text == "大家好，欢迎来到直播间"
 
-    def test_invalid_video_url_not_mp4(self):
+    def test_invalid_video_url_unsupported_ext(self):
         from app.schemas.lipsync import CreateLipsyncJobRequest
 
-        with pytest.raises(ValueError, match="MP4"):
+        # 不支持的扩展名（.txt）应报错
+        with pytest.raises(ValueError, match="格式不支持"):
             CreateLipsyncJobRequest(
-                video_url="https://example.com/video.mov",
+                video_url="https://example.com/video.txt",
                 voice_id="longxiaochun_v3",
                 script_text="测试文本",
             )
 
+    def test_mov_video_url_accepted(self):
+        from app.schemas.lipsync import CreateLipsyncJobRequest
+
+        # .MOV 是 iPhone 拍摄的常见容器，h264 编码可直接被 MediaKit 处理
+        req = CreateLipsyncJobRequest(
+            video_url="https://example.com/video.mov",
+            audio_url="https://example.com/audio.mp3",
+        )
+        assert req.video_url.endswith(".mov")
+
     def test_invalid_video_url_empty(self):
         from app.schemas.lipsync import CreateLipsyncJobRequest