Add inline comments to core modules and code review notes

Added explanatory comments to server.py, freshrss_pipeline.py, pipeline.py,
freshrss.py, keyword_index.py, summary_loop.py, and filters/engine.py.
Also added CODE_REVIEW.md with prioritized improvement suggestions.

src/summary_mcp/server.py

@@ -1,5 +1,8 @@
 from __future__ import annotations
 
+# MCP 服务入口：将内容提取、过滤、FreshRSS 全链路管道暴露为 MCP 工具。
+# 生产主入口是 run_freshrss_openclaw_pipeline，其余工具供单步调试使用。
+
 import json
 import tempfile
 from datetime import date
@@ -22,6 +25,7 @@ mcp = FastMCP(name="content-extract-mcp")
 
 @mcp.tool()
 def extract_url_content(url: str, language_hint: str | None = None) -> dict:
+    # 从单个 URL 抓取并提取结构化文章内容，供单步调试使用
     """Extract structured article content from a single URL."""
     result = extract_content(
         ExtractionInput(
@@ -34,6 +38,7 @@ def extract_url_content(url: str, language_hint: str | None = None) -> dict:
 
 @mcp.tool()
 def extract_item_content(item: dict) -> dict:
+    # 从已标准化的 item 对象提取内容（跳过网络抓取，使用 RSS 内联内容）
     """Extract structured article content from a normalized item object."""
     parsed_item = Item.model_validate(item)
     result = extract_content(ExtractionInput(item=parsed_item))
@@ -47,6 +52,7 @@ def filter_summary_result(
     item: dict | None = None,
     context: dict | None = None,
 ) -> dict:
+    # 对结构化摘要结果运行确定性规则引擎，返回 keep/review/drop 决策
     """Apply deterministic filter rules to a structured summary result."""
     parsed_summary = LlmSummaryResult.model_validate(summary_result)
     parsed_article = ExtractedArticle.model_validate(extracted_article) if extracted_article else None
@@ -88,6 +94,7 @@ def run_freshrss_openclaw_pipeline(
     include_item_reports: bool = False,
 ) -> dict:
     """Run the full FreshRSS -> extract -> LLM -> filter -> OpenClaw payload pipeline."""
+    # context 若传入则序列化为临时文件再传给 pipeline（TODO: pipeline 改为直接接受 dict）
     temp_context_path: Path | None = None
 
     try: