Merge pull request 'fix(kb_workflow): resolve module/package naming conflict' (#30) from fix/crawler-proxy-config into main

Reviewed-on: http://192.168.1.22:8418/starmen1265/kb-skills/pulls/30

kb_workflow/__init__.py

@@ -3,6 +3,6 @@
 知识库工作流管道入口。
 """
 
-from .kb_workflow import process_command, main
+from .cli import process_command, main
 
 __all__ = ["process_command", "main"]

kb_workflow/__main__.py

@@ -0,0 +1,12 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+KB Workflow 包入口点
+
+支持通过 python -m kb_workflow 直接运行 CLI。
+"""
+
+from .cli import main
+
+if __name__ == '__main__':
+    main()

kb_workflow/cli.py

@@ -9,11 +9,15 @@ KB Workflow - Knowledge Base Workflow Orchestrator
 内部使用 kb_workflow.pipeline 包实现完整的内容处理流程。
 
 使用方式:
-    python kb_workflow.py process "https://www.bilibili.com/video/BVxxx"
-    python kb_workflow.py process "https://..." -o /path/to/output
-    python kb_workflow.py login                    # QR code login
-    python kb_workflow.py login --import-cookie cookies.json
-    python kb_workflow.py login --status
+    python -m kb_workflow process "https://www.bilibili.com/video/BVxxx"
+    python -m kb_workflow process "https://..." -o /path/to/output
+    python -m kb_workflow login                    # QR code login
+    python -m kb_workflow login --import-cookie cookies.json
+    python -m kb_workflow login --status
+
+或者通过包接口调用:
+    from kb_workflow import process_command
+    result = process_command("https://...")
 """
 
 import argparse
@@ -41,13 +45,13 @@ def process_command(
         Dictionary with success status, content_dir, and results
     """
     try:
-        from kb_workflow.pipeline.config import get_settings
-        from kb_workflow.pipeline.pipeline import Pipeline
-        from kb_workflow.pipeline.processors import (
+        from .pipeline.config import get_settings
+        from .pipeline.pipeline import Pipeline
+        from .pipeline.processors import (
             ASRProcessor, AnalyzeProcessor, ArchiveProcessor,
             DownloadProcessor, ParseProcessor
         )
-        from kb_workflow.pipeline.schemas import PipelineConfig
+        from .pipeline.schemas import PipelineConfig
 
         async def run_pipeline():
             # Determine output directory - default to intermediate_path
@@ -119,9 +123,9 @@ def login_command(
         Dictionary with login result
     """
     try:
-        from kb_workflow.auth import ZhihuLogin
-        from kb_workflow.auth.cookie_manager import CookieManager, parse_json_cookies
-        from kb_workflow.pipeline.config import get_settings
+        from .auth import ZhihuLogin
+        from .auth.cookie_manager import CookieManager, parse_json_cookies
+        from .pipeline.config import get_settings
 
         settings = get_settings()
         manager = CookieManager()
@@ -175,22 +179,22 @@ def main():
         epilog='''
 使用示例:
   # 处理URL (通过完整管道)
-  python kb_workflow.py process "https://www.bilibili.com/video/BVxxx"
+  python -m kb_workflow process "https://www.bilibili.com/video/BVxxx"
 
   # 指定输出目录
-  python kb_workflow.py process "https://..." -o /path/to/output
+  python -m kb_workflow process "https://..." -o /path/to/output
 
   # 强制重新执行（忽略已完成状态）
-  python kb_workflow.py process "https://..." --no-skip
+  python -m kb_workflow process "https://..." --no-skip
 
   # 知乎登录 (二维码扫码)
-  python kb_workflow.py login
+  python -m kb_workflow login
 
   # 导入 Cookie
-  python kb_workflow.py login --import-cookie cookies.json
+  python -m kb_workflow login --import-cookie cookies.json
 
   # 检查 Cookie 状态
-  python kb_workflow.py login --status
+  python -m kb_workflow login --status
         '''
     )
 

kb_workflow/crawler/config.py

@@ -54,7 +54,7 @@ class CrawlerConfig(BaseModel):
 
     # Proxy settings
     proxy: Optional[ProxyConfig] = Field(None, description="Proxy configuration")
-    proxy_required: bool = Field(default=True, description="Whether proxy is mandatory")
+    proxy_required: bool = Field(default=False, description="Whether proxy is mandatory (False for 旁路由 auto-proxy)")
 
     # Rate limiting
     min_delay: float = Field(default=1.0, description="Minimum delay between requests (seconds)")