From 7ac4937c487a953d7b674b6793545b910879d505 Mon Sep 17 00:00:00 2001
From: starmen1265 <starmen1265@163.com>
Date: Sat, 21 Mar 2026 21:41:29 +0800
Subject: [PATCH] fix(deep-analyzer, srt): correct Zhipu API thinking parameter
 and fix metadata handling

Root cause:
1. thinking.type="disabled" caused ASR correction accuracy degradation
2. SRTProcessor didn't flatten nested metadata structure
3. Low-quality auto-generated summary section
4. duration field type handling issue

Changes:
- DeepAnalyzer: Remove thinking.type="disabled" to enable default thinking mode
- SRTProcessor: Add metadata flattening for nested structures
- SRTProcessor: Remove low-quality summary section generation
- SRTProcessor: Add duration type checking (string or int)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---
 kb_workflow/deep_analyzer/__init__.py  | 18 +++++++------
 kb_workflow/pipeline/processors/srt.py | 36 ++++++++++++++++----------
 2 files changed, 33 insertions(+), 21 deletions(-)

diff --git a/kb_workflow/deep_analyzer/__init__.py b/kb_workflow/deep_analyzer/__init__.py
index 4b06248..974d077 100644
--- a/kb_workflow/deep_analyzer/__init__.py
+++ b/kb_workflow/deep_analyzer/__init__.py
@@ -95,28 +95,30 @@ class SimpleAIClient:
         base_url = base_url or "https://open.bigmodel.cn/api/coding/paas/v4"
         url = f"{base_url}/chat/completions"
         headers = {"Authorization": f"Bearer {api_key}"}
-        # GLM-4.5/4.6/4.7/5 默认启用thinking mode，使用 thinking.type 参数禁用
+        # GLM-4.5/4.6/4.7/5 默认启用thinking mode
+        # 移除 thinking.type="disabled"，让AI使用默认思考模式以提高准确性
         payload = {
             "model": model,
             "messages": [{"role": "user", "content": prompt}],
-            "max_tokens": max_tokens,
-            "thinking": {
-                "type": "disabled"  # 禁用思考模式，获取直接响应
-            }
+            "max_tokens": max_tokens
         }
         response = requests.post(url, headers=headers, json=payload, timeout=600)
         response.raise_for_status()
         data = response.json()
         message = data.get('choices', [{}])[0].get('message', {})
+
+        # 优先返回 content 字段
         content = message.get('content', '')
 
+        # 如果 content 为空但有 reasoning_content，使用 reasoning_content
         if not content:
-            # 如果仍然为空，检查是否有reasoning_content（用于调试）
             reasoning = message.get('reasoning_content', '')
             if reasoning:
-                print(f"[DEBUG] Zhipu API返回空的content，但有reasoning_content。", file=sys.stderr)
-                print(f"[DEBUG] 这可能表示thinking.type参数未生效或模型不支持。", file=sys.stderr)
+                print(f"[DEBUG] Zhipu API返回空的content，使用reasoning_content。", file=sys.stderr)
                 print(f"[DEBUG] reasoning_content前200字符: {reasoning[:200]}", file=sys.stderr)
+                content = reasoning
+
+        if not content:
             raise ValueError(f"Zhipu API返回空内容。请检查API配置和模型参数。响应数据: {data}")
 
         return content
diff --git a/kb_workflow/pipeline/processors/srt.py b/kb_workflow/pipeline/processors/srt.py
index 2723e38..ecf7f7a 100644
--- a/kb_workflow/pipeline/processors/srt.py
+++ b/kb_workflow/pipeline/processors/srt.py
@@ -166,7 +166,7 @@ class SRTProcessor(BaseProcessor):
             metadata_file: 元数据文件路径
 
         Returns:
-            元数据字典
+            元数据字典（扁平化后的）
         """
         path = Path(metadata_file)
         if not path.exists():
@@ -174,7 +174,21 @@ class SRTProcessor(BaseProcessor):
             return {}
 
         with open(path, 'r', encoding='utf-8') as f:
-            return json.load(f)
+            raw_metadata = json.load(f)
+
+        # 扁平化嵌套结构（与 AnalyzeProcessor._normalize_metadata 一致）
+        if not raw_metadata:
+            return {}
+
+        # 如果已经是扁平结构（顶层有 title）
+        if 'title' in raw_metadata:
+            return raw_metadata
+
+        # 处理嵌套结构 {metadata: {...}, stats: {...}}
+        if 'metadata' in raw_metadata:
+            return raw_metadata['metadata'].copy()
+
+        return raw_metadata
 
     def _extract_tags(self, paragraphs: List[str]) -> List[str]:
         """从段落中提取标签
@@ -216,16 +230,7 @@ class SRTProcessor(BaseProcessor):
         # 构建内容
         content_parts = [frontmatter, ""]
 
-        # 添加摘要（可选）
-        if paragraphs:
-            content_parts.append("## 摘要")
-            content_parts.append("")
-            # 使用第一段作为简单摘要
-            first_para = paragraphs[0][:200] if len(paragraphs[0]) > 200 else paragraphs[0]
-            content_parts.append(first_para + ("..." if len(paragraphs[0]) > 200 else ""))
-            content_parts.append("")
-
-        # 添加内容
+        # 直接添加内容，不生成摘要部分
         content_parts.append("## 内容")
         content_parts.append("")
         for para in paragraphs:
@@ -271,7 +276,12 @@ class SRTProcessor(BaseProcessor):
         # 时长（视频）
         duration = metadata.get('duration', 0)
         if duration:
-            duration_str = self._format_duration(duration)
+            # 如果 duration 已经是字符串格式（如 "05:42"），直接使用
+            # 否则（整数秒数）调用 _format_duration 转换
+            if isinstance(duration, str):
+                duration_str = duration
+            else:
+                duration_str = self._format_duration(duration)
             lines.append(f'duration: {duration_str}')
 
         # BVID