fix(analyze): extract text from Whisper JSON format

- Handle Whisper transcription format (array of segments with text)
- Extract full text from transcription array before passing to DeepAnalyzer
- Fix offsets parsing to support both dict and list formats

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

kb_pipeline/processors/analyze.py

@@ -81,6 +81,15 @@ class AnalyzeProcessor(BaseProcessor):
             metadata = self._load_json(input_data.metadata_file)
             content = self._load_json(input_data.content_file)
 
+            # 处理 Whisper 字幕格式 - 提取完整文本
+            if content and 'transcription' in content:
+                # Whisper JSON 格式，提取文本
+                text_parts = []
+                for item in content.get('transcription', []):
+                    text_parts.append(item.get('text', ''))
+                content = {'text': ' '.join(text_parts)}
+                logger.info(f"Extracted {len(content['text'])} chars from Whisper transcription")
+
             # 对于文章类型，内容可能是纯文本文件
             if not content and input_data.content_type in ("article", "answer", "zhuanlan"):
                 content_path = Path(input_data.content_file)