feat(screener): ai_news pipeline (top-100 parallel, fail-soft, upsert)

stock-lab/tests/test_ai_news_pipeline.py

@@ -0,0 +1,110 @@
+import datetime as dt
+import sqlite3
+import pytest
+from unittest.mock import AsyncMock, MagicMock, patch
+
+from app.screener.ai_news import pipeline
+from app.screener.schema import ensure_screener_schema
+
+
+@pytest.fixture
+def conn():
+    c = sqlite3.connect(":memory:")
+    c.row_factory = sqlite3.Row
+    ensure_screener_schema(c)
+    # 시총 상위 3종목 시드
+    c.execute("INSERT INTO krx_master (ticker, name, market, market_cap, updated_at) "
+              "VALUES (?, ?, 'KOSPI', ?, datetime('now'))", ("005930", "삼성전자", 9_000_000))
+    c.execute("INSERT INTO krx_master (ticker, name, market, market_cap, updated_at) "
+              "VALUES (?, ?, 'KOSPI', ?, datetime('now'))", ("000660", "SK하이닉스", 8_000_000))
+    c.execute("INSERT INTO krx_master (ticker, name, market, market_cap, updated_at) "
+              "VALUES (?, ?, 'KOSPI', ?, datetime('now'))", ("373220", "LG에너지솔루션", 7_000_000))
+    c.commit()
+    yield c
+    c.close()
+
+
+@pytest.mark.asyncio
+async def test_refresh_daily_happy_path(conn):
+    """3종목 mini integration — 각 종목별로 scraper/analyzer mock."""
+    asof = dt.date(2026, 5, 13)
+    fake_news = [{"title": "헤드라인"}]
+
+    async def fake_fetch(client, ticker, n):
+        return fake_news
+
+    scores_by_ticker = {
+        "005930": 7.5, "000660": 4.0, "373220": -6.0,
+    }
+    async def fake_score(llm, ticker, news, *, name=None, model="m"):
+        return {
+            "ticker": ticker, "score_raw": scores_by_ticker[ticker],
+            "reason": f"r{ticker}", "news_count": 1,
+            "tokens_input": 100, "tokens_output": 20, "model": model,
+        }
+
+    with patch.object(pipeline, "_scraper") as ms, \
+         patch.object(pipeline, "_analyzer") as ma, \
+         patch.object(pipeline, "_make_llm") as ml, \
+         patch.object(pipeline, "_make_http") as mh:
+        ms.fetch_news = fake_fetch
+        ma.score_sentiment = fake_score
+        ml.return_value.__aenter__.return_value = AsyncMock()
+        ml.return_value.__aexit__.return_value = None
+        mh.return_value.__aenter__.return_value = AsyncMock()
+        mh.return_value.__aexit__.return_value = None
+        result = await pipeline.refresh_daily(conn, asof, concurrency=3, rate_limit_sec=0)
+
+    assert result["asof"] == "2026-05-13"
+    assert result["updated"] == 3
+    assert result["failures"] == []
+    assert len(result["top_pos"]) == 3
+    assert result["top_pos"][0]["ticker"] == "005930"  # 가장 큰 점수
+    assert result["top_neg"][0]["ticker"] == "373220"  # 가장 작은 점수
+    assert result["tokens_input"] == 300
+    assert result["tokens_output"] == 60
+
+    # DB upsert 확인
+    rows = conn.execute("SELECT ticker, score_raw FROM news_sentiment WHERE date=?",
+                        ("2026-05-13",)).fetchall()
+    assert len(rows) == 3
+    by_ticker = {r["ticker"]: r["score_raw"] for r in rows}
+    assert by_ticker["005930"] == 7.5
+    assert by_ticker["373220"] == -6.0
+
+
+@pytest.mark.asyncio
+async def test_refresh_daily_failures_isolated(conn):
+    """한 종목이 예외 던져도 나머지 종목은 정상 처리."""
+    asof = dt.date(2026, 5, 13)
+
+    async def fake_fetch(client, ticker, n):
+        return [{"title": "h"}]
+
+    async def fake_score(llm, ticker, news, *, name=None, model="m"):
+        if ticker == "000660":
+            raise RuntimeError("llm exploded")
+        return {
+            "ticker": ticker, "score_raw": 5.0, "reason": "r", "news_count": 1,
+            "tokens_input": 100, "tokens_output": 20, "model": model,
+        }
+
+    with patch.object(pipeline, "_scraper") as ms, \
+         patch.object(pipeline, "_analyzer") as ma, \
+         patch.object(pipeline, "_make_llm") as ml, \
+         patch.object(pipeline, "_make_http") as mh:
+        ms.fetch_news = fake_fetch
+        ma.score_sentiment = fake_score
+        ml.return_value.__aenter__.return_value = AsyncMock()
+        ml.return_value.__aexit__.return_value = None
+        mh.return_value.__aenter__.return_value = AsyncMock()
+        mh.return_value.__aexit__.return_value = None
+        result = await pipeline.refresh_daily(conn, asof, concurrency=3, rate_limit_sec=0)
+
+    assert result["updated"] == 2
+    assert len(result["failures"]) == 1
+
+
+def test_top_market_cap_tickers(conn):
+    out = pipeline._top_market_cap_tickers(conn, n=2)
+    assert out == ["005930", "000660"]