fix(asr): use content_dir for subtitle output instead of video_path

- Add content_dir field to ASRInput schema
- Pass content_dir from pipeline when creating ASRInput
- Modify _try_official_subtitle to use content_dir for output
- Modify _run_whisper_basic to use content_dir for output
- Add validation for empty video_path in Whisper fallback

Root cause: DownloadProcessor sets content_file="" for video types,
causing Path("").parent to resolve to current directory instead of
content directory. Subtitle files were written to wrong location.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

kb_pipeline/processors/asr.py

@@ -172,9 +172,10 @@ class ASRProcessor:
         Note:
             无字幕返回 None（不是抛异常），让流程继续到 Whisper
         """
-        video_path = Path(input_data.video_path)
-        output_dir = video_path.parent
-        base_name = video_path.stem
+        # 使用 content_dir 作为输出目录（而不是从 video_path 推断）
+        output_dir = Path(input_data.content_dir)
+        # 使用 content_id 作为基础文件名
+        base_name = f"{input_data.platform}_{input_data.content_id}_subtitle"
 
         # 输出文件路径
         txt_path = output_dir / f"{base_name}.txt"
@@ -343,11 +344,18 @@ class ASRProcessor:
             ASR 处理结果
 
         Raises:
-            RuntimeError: Whisper.cpp 路径不存在或执行失败
+            RuntimeError: Whisper.cpp 路径不存在或执行失败，或 video_path 为空
         """
+        # 检查 video_path 是否有效
+        if not input_data.video_path:
+            raise RuntimeError(
+                "video_path 为空，无法执行 Whisper 语音识别。"
+                "请确保视频文件已下载（对于没有官方字幕的视频，需要先下载视频文件）。"
+            )
+
         video_path = Path(input_data.video_path)
-        output_dir = video_path.parent
-        base_name = video_path.stem
+        output_dir = Path(input_data.content_dir)
+        base_name = f"{input_data.platform}_{input_data.content_id}_whisper"
 
         # 获取 Whisper.cpp 路径
         try: