fix(srt): add disable_reasoning parameter for ASR correction and include title in archive filename

- SimpleAIClient: Add disable_reasoning parameter to control AI thinking mode
- ASRCorrector: Use disable_reasoning=True to get direct correction results
- ArchiveProcessor: Extract title from frontmatter and include in filename

File naming format: {YYYYMMDD}_{content_id}_{title}_analysis.md

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

kb_workflow/deep_analyzer/__init__.py

@@ -37,20 +37,25 @@ class AnalysisResult:
 class SimpleAIClient:
     """AI 客户端"""
 
-    def __init__(self, api_key: str = None, provider: str = None, model: str = None, base_url: str = None):
+    def __init__(self, api_key: str = None, provider: str = None, model: str = None, base_url: str = None, disable_reasoning: bool = False):
         self.api_key = api_key or os.environ.get("AI_API_KEY", "")
         self.provider = provider or os.environ.get("AI_PROVIDER", "")
         self.model = model or os.environ.get("AI_MODEL", "glm-5")
         self.base_url = base_url or os.environ.get("AI_BASE_URL", "")
         self.max_retries = 3
+        self.disable_reasoning = disable_reasoning
 
-    def generate(self, prompt: str, max_tokens: int = 16000) -> str:
+    def generate(self, prompt: str, max_tokens: int = 16000, disable_reasoning: bool = None) -> str:
         """生成文本"""
         api_key = os.environ.get("AI_API_KEY", self.api_key)
         provider = os.environ.get("AI_PROVIDER", self.provider)
         model = os.environ.get("AI_MODEL", self.model)
         base_url = os.environ.get("AI_BASE_URL", self.base_url)
 
+        # 确定 disable_reasoning 的值：优先使用参数，否则使用实例变量
+        if disable_reasoning is None:
+            disable_reasoning = self.disable_reasoning
+
         if not api_key:
             raise ValueError("AI_API_KEY 未设置")
 
@@ -63,7 +68,7 @@ class SimpleAIClient:
                 if provider == "openai":
                     result = self._call_openai(prompt, max_tokens, api_key, model, base_url)
                 elif provider == "zhipu":
-                    result = self._call_zhipu(prompt, max_tokens, api_key, model, base_url)
+                    result = self._call_zhipu(prompt, max_tokens, api_key, model, base_url, disable_reasoning)
                 elif provider == "minimax":
                     result = self._call_minimax(prompt, max_tokens, api_key, model, base_url)
                 else:
@@ -88,7 +93,7 @@ class SimpleAIClient:
         response.raise_for_status()
         return response.json()['choices'][0]['message']['content']
 
-    def _call_zhipu(self, prompt: str, max_tokens: int, api_key: str, model: str, base_url: str) -> str:
+    def _call_zhipu(self, prompt: str, max_tokens: int, api_key: str, model: str, base_url: str, disable_reasoning: bool = False) -> str:
         import requests
         import sys
 
@@ -96,22 +101,28 @@ class SimpleAIClient:
         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
-        # 移除 thinking.type="disabled"，让AI使用默认思考模式以提高准确性
+        # 通过 disable_reasoning 参数控制是否禁用思考模式
         payload = {
             "model": model,
             "messages": [{"role": "user", "content": prompt}],
             "max_tokens": max_tokens
         }
+
+        # 如果明确要求禁用思考模式，添加 thinking 参数
+        if disable_reasoning:
+            payload["thinking"] = {"type": "disabled"}
         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
+        # 返回 content 字段
+        # 当禁用思考模式时，content 包含直接答案
+        # 当启用思考模式时，content 可能包含思考过程和分析
         content = message.get('content', '')
 
-        # 如果 content 为空但有 reasoning_content，使用 reasoning_content
         if not content:
+            # 如果 content 为空，检查是否有 reasoning_content
             reasoning = message.get('reasoning_content', '')
             if reasoning:
                 print(f"[DEBUG] Zhipu API返回空的content，使用reasoning_content。", file=sys.stderr)

kb_workflow/pipeline/processors/archive.py

@@ -7,6 +7,7 @@ to the archive directory organized by platform.
 from __future__ import annotations
 
 import logging
+import re
 import shutil
 from datetime import datetime
 from pathlib import Path
@@ -65,9 +66,14 @@ class ArchiveProcessor(BaseProcessor):
             platform_dir = archive_base / input_data.platform
             platform_dir.mkdir(parents=True, exist_ok=True)
 
-            # 文件命名: {YYYYMMDD}_{content_id}_analysis.md
+            # 从源文件中提取标题（用于文件命名）
+            title = self._extract_title_from_file(Path(input_data.analysis_file))
+            # 清理标题：移除特殊字符，限制长度
+            safe_title = self._sanitize_title(title) if title else input_data.content_id
+
+            # 文件命名: {YYYYMMDD}_{content_id}_{title}_analysis.md
             timestamp = datetime.now().strftime("%Y%m%d")
-            archive_filename = f"{timestamp}_{input_data.content_id}_analysis.md"
+            archive_filename = f"{timestamp}_{input_data.content_id}_{safe_title}_analysis.md"
             archive_path = platform_dir / archive_filename
 
             # Step 3: 检查重复
@@ -147,6 +153,64 @@ class ArchiveProcessor(BaseProcessor):
         matches = list(platform_dir.glob(pattern))
         return matches[0] if matches else None
 
+    def _extract_title_from_file(self, file_path: Path) -> Optional[str]:
+        """从 Markdown 文件的 frontmatter 中提取标题
+
+        Args:
+            file_path: Markdown 文件路径
+
+        Returns:
+            标题字符串，如果未找到返回 None
+        """
+        try:
+            content = file_path.read_text(encoding='utf-8')
+
+            # 查找 frontmatter 中的 title 字段
+            # 格式：title: "标题内容" 或 title: 标题内容
+            title_match = re.search(r'^title:\s*(?:"([^"]*)"|(.+))$', content, re.MULTILINE)
+
+            if title_match:
+                # 优先使用引号内的内容，否则使用第二个捕获组
+                title = title_match.group(1) or title_match.group(2)
+                return title.strip() if title else None
+
+            return None
+        except Exception as e:
+            logger.warning(f"Failed to extract title from {file_path}: {e}")
+            return None
+
+    def _sanitize_title(self, title: str) -> str:
+        """清理标题用于文件命名
+
+        移除特殊字符，限制长度，转换为安全的文件名。
+
+        Args:
+            title: 原始标题
+
+        Returns:
+            清理后的标题
+        """
+        # 移除或替换不适合文件名的字符
+        # 保留中文、字母、数字、下划线、连字符
+        # 替换所有特殊字符（包括标点符号和常见符号）
+        safe = re.sub(r'[\\/:*?"<>|，。！？、；：""\'\'\s@#$%&*+\-=\[\]{}()<>]+', '_', title)
+
+        # 移除连续的下划线
+        safe = re.sub(r'_+', '_', safe)
+
+        # 去除首尾下划线和空格
+        safe = safe.strip('_')
+
+        # 限制长度（避免文件名过长）
+        if len(safe) > 50:
+            safe = safe[:50]
+
+        # 如果清理后为空，返回默认值
+        if not safe:
+            safe = "untitled"
+
+        return safe
+
     def _ask_overwrite(self, existing_file: Path, is_non_interactive: bool = False) -> bool:
         """询问用户是否覆盖已存在的文件
 

kb_workflow/srt/corrector.py

@@ -100,7 +100,8 @@ class ASRCorrector:
         """
         try:
             prompt = CORRECTION_PROMPT.format(text=text)
-            result = self.ai_client.generate(prompt, max_tokens=len(text) + 500)
+            # ASR 纠错需要直接结果，不需要 AI 的分析过程，因此禁用思考模式
+            result = self.ai_client.generate(prompt, max_tokens=len(text) + 500, disable_reasoning=True)
             return result.strip()
         except Exception as e:
             logger.warning(f"ASR correction failed: {e}, returning original text")