feat: Phase 2 新闻打分去重与 Agent 输入池裁剪

标题相似度合并、信源/时效/昨日重复加权排序,Agent 模式扩大 LLM 新闻候选池并记录抓取失败源。

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
2026-07-03 14:53:30 +08:00
parent 728bd1b9d1
commit 391f887d73
6 changed files with 370 additions and 46 deletions

View File

@@ -49,6 +49,7 @@ from daily.news.fetch import (
prepare_wecom_cn_news_items,
prepare_wecom_news_items,
)
from daily.news.rank import apply_news_ranking
from daily.report_data import (
build_full_payload,
build_llm_input,
@@ -439,6 +440,8 @@ def generate_report() -> tuple[str, str, Path, Path]:
topic_name, github_topic = fetch_topic_hot_repos(topic_fetch_n, exclude=seen_repos)
ai_news = fetch_ai_news()
cn_ai_news = fetch_cn_ai_news()
ai_news = apply_news_ranking(ai_news, date_str=date_str)
cn_ai_news = apply_news_ranking(cn_ai_news, date_str=date_str)
wecom_limits = {
"trending": wecom_trending,
@@ -463,6 +466,7 @@ def generate_report() -> tuple[str, str, Path, Path]:
ai_news=ai_news,
cn_ai_news=cn_ai_news,
wecom_limits=wecom_limits,
agent_mode=is_agent_mode(),
)
save_json(
data_json_path(date_str),