fix(data): fulltext 段补 --limit 预算门(三跑冒烟7分钟马拉松) [nas]

_run_fulltext 漏门:new_articles 跨股去重后仍可远超 N(冒烟 2 股×100条 →~150 art @2.3s);真实运行有墙钟兜底故非事故,冒烟语义补齐+回归钉死
2026-09-06 23:56:05 +08:00
parent 407fcec513
commit 594e2efbf5
2 changed files with 13 additions and 0 deletions
@@ -477,6 +477,17 @@ def test_daily_limit_is_per_stage_and_bounds_pdf_fivecat(root, monkeypatch):
    assert news_calls == 1            # news 段独立预算未被 ann 挤占


+def test_daily_limit_bounds_fulltext_stage(root, monkeypatch):
+    """回归(三跑冒烟超时): fulltext 段漏预算门——new_articles 去重后仍可
+    远超 N(2 股×100 条 → ~150 art),冒烟变 7 分钟马拉松。"""
+    two_arts = [{"code": f"art{i}", "date": "2026-09-06 10:00:00",
+                 "title": f"t{i}", "content": "c", "mediaName": "m", "image": ""}
+                for i in (1, 2)]
+    _wire_daily(monkeypatch, root, news_rows=two_arts)
+    cd.run_lane("daily", limit=2)
+    assert cd.fetch_article_html.call_count == 2   # 预算 2,非 4(2股×2art)
+
+
 def test_daily_express_title_routes_to_pdf(root, monkeypatch):
    """标题含「业绩快报」→ 进当日 PDF 待下清单(无服务端码,客户端谓词)。"""
    todo = cd.collect_pdf_candidates(