feat(08-02): add CommentData models for comment crawling

- Add CommentAuthor model for comment author info
- Add CommentData model with content, author, likes, child_count
- Add CommentsResult model for crawl operation result
- Update CrawlResult to include optional comments field

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

kb_workflow/crawler/models.py

@@ -3,7 +3,7 @@
 Pydantic models for structured data from Zhihu API responses.
 """
 
-from typing import Optional, Union
+from typing import Optional, Union, List
 from pydantic import BaseModel, Field
 
 
@@ -79,6 +79,56 @@ class ArticleData(BaseModel):
     )
 
 
+class CommentAuthor(BaseModel):
+    """Comment author information.
+
+    Attributes:
+        name: Author display name
+        url_token: Author URL token (e.g., 'zhang-san-12')
+    """
+    name: str = Field(..., description="Author display name")
+    url_token: Optional[str] = Field(None, description="Author URL token")
+
+
+class CommentData(BaseModel):
+    """Data model for Zhihu comment.
+
+    Attributes:
+        id: Comment ID
+        content: Comment content in plain text
+        author: Comment author information
+        created_time: Unix timestamp of creation
+        like_count: Number of likes/upvotes
+        child_count: Number of child/reply comments
+        is_author: Whether the commenter is the content author
+    """
+    id: int = Field(..., description="Comment ID")
+    content: str = Field(default="", description="Comment content")
+    author: Optional[CommentAuthor] = Field(None, description="Comment author")
+    created_time: Optional[int] = Field(None, description="Creation timestamp")
+    like_count: int = Field(default=0, description="Like/upvote count")
+    child_count: int = Field(default=0, description="Number of child comments")
+    is_author: bool = Field(default=False, description="Whether commenter is content author")
+
+
+class CommentsResult(BaseModel):
+    """Result of comment crawling operation.
+
+    Attributes:
+        content_type: Type of content ("answers" or "articles")
+        content_id: ID of the content
+        comments: List of comments
+        total_count: Total number of comments (may exceed returned count)
+    """
+    content_type: str = Field(..., description="Content type: answers or articles")
+    content_id: int = Field(..., description="Content ID")
+    comments: List[CommentData] = Field(
+        default_factory=list,
+        description="List of comments"
+    )
+    total_count: int = Field(default=0, description="Total comment count")
+
+
 class CrawlResult(BaseModel):
     """Result of a crawl operation.
 
@@ -86,6 +136,7 @@ class CrawlResult(BaseModel):
         success: Whether the crawl was successful
         content_type: Type of content ("answer" or "article")
         data: Extracted content data if successful
+        comments: Optional list of comments (when include_comments=True)
         error: Error message if failed
     """
     success: bool = Field(..., description="Whether crawl succeeded")
@@ -94,4 +145,8 @@ class CrawlResult(BaseModel):
         None,
         description="Extracted content data"
     )
+    comments: Optional[List[CommentData]] = Field(
+        None,
+        description="Comments if include_comments was True"
+    )
     error: Optional[str] = Field(None, description="Error message if failed")