shaguabijia-app-server/tests/test_compare_alert_stuck_worker.py

"""build_hits 集成测:cancelled trace 优先/保底切换、failed 附卡点、限量。"""
import json
from pathlib import Path

from app.core.compare_alert_worker import _fmt_stuck, build_hits
from app.services.trace_stuck import StuckPoint


class _Rec:
    def __init__(self, **kw):
        self.trace_id = kw.get("trace_id", "t")
        self.status = kw.get("status", "cancelled")
        self.total_ms = kw.get("total_ms")
        self.step_count = kw.get("step_count")
        self.fail_reason = kw.get("fail_reason")
        self.information = kw.get("information")
        self.app_version = kw.get("app_version")
        self.created_at = kw.get("created_at")
        self.trace_url = kw.get("trace_url")
        self.user_id = kw.get("user_id")


def _frame(pdir: Path, idx: int, step: str, page: str) -> None:
    pdir.mkdir(parents=True, exist_ok=True)
    body = {"pipeline_step": step, "detected_page": page, "windows": [{"n": ["x" * 200]}]}
    (pdir / f"step_{idx:03d}.json").write_text(
        json.dumps(body, ensure_ascii=False), encoding="utf-8"
    )


_KW = dict(
    stuck_threshold=15, max_tail=40, max_trace_reads=30,
    cancelled_ms_threshold=90000, cancelled_step_threshold=30,
    timeout_keywords=("超时",), unrecognized_keywords=("未识别",), biz_exclude_keywords=(),
)


def test_cancelled_stuck_reports_via_trace(tmp_path):
    for i in range(18):
        _frame(tmp_path / "20260804_x" / "meituan", i, "add_one_dish", "meal_detail_popup")
    rec = _Rec(status="cancelled", trace_url="https://x/traces/20260804_x/",
               total_ms=5000, step_count=3)  # 保底不会中,靠 trace 判卡死
    hits = build_hits([rec], work_log_dir=str(tmp_path), **_KW)
    assert len(hits) == 1
    assert hits[0].alert_type == "T5"
    assert hits[0].reason == "深度放弃"
    assert "美团·加菜" in hits[0].stuck_point
    assert "帧" in hits[0].stuck_point


def test_cancelled_readable_not_stuck_long_duration_reports(tmp_path):
    # trace 可读但没判出原地卡点:仍过耗时/步数阈值兜底,超长(>90s)照报 T5,卡点列留空。
    # (线上 trace 几乎总可读,若不回退则 total_ms 阈值形同虚设、超长放弃永不报——见 compare-fail-alert 排查。)
    p = tmp_path / "20260804_y" / "eleme"
    _frame(p, 0, "set_address", "home")
    for i in range(1, 6):
        _frame(p, i, "enter_store", "store")
    rec = _Rec(status="cancelled", trace_url="https://x/traces/20260804_y/",
               total_ms=95000, step_count=40)
    hits = build_hits([rec], work_log_dir=str(tmp_path), **_KW)
    assert len(hits) == 1
    assert hits[0].alert_type == "T5"
    assert hits[0].reason == "深度放弃"
    assert hits[0].stuck_point is None  # 没卡点 → 卡片卡点列显 "-"


def test_cancelled_readable_not_stuck_short_no_report(tmp_path):
    # trace 可读没卡点、且耗时/步数都没超阈值 → 正常早退,不报(兜底阈值把住,不误报)。
    p = tmp_path / "20260804_ys" / "eleme"
    _frame(p, 0, "set_address", "home")
    for i in range(1, 6):
        _frame(p, i, "enter_store", "store")
    rec = _Rec(status="cancelled", trace_url="https://x/traces/20260804_ys/",
               total_ms=5000, step_count=3)
    hits = build_hits([rec], work_log_dir=str(tmp_path), **_KW)
    assert hits == []


def test_cancelled_unreadable_falls_back(tmp_path):
    rec = _Rec(status="cancelled", trace_url="https://x/traces/nope/",
               total_ms=95000, step_count=3)
    hits = build_hits([rec], work_log_dir=str(tmp_path), **_KW)
    assert len(hits) == 1
    assert hits[0].alert_type == "T5" and "深度放弃" in hits[0].reason


def test_no_work_log_dir_uses_fallback(tmp_path):
    rec = _Rec(status="cancelled", trace_url="https://x/traces/y/",
               total_ms=95000, step_count=3)
    hits = build_hits([rec], work_log_dir="", **_KW)
    assert len(hits) == 1 and "深度放弃" in hits[0].reason


def test_failed_gets_stuck_point_appended(tmp_path):
    for i in range(20):
        _frame(tmp_path / "20260804_f" / "meituan", i, "add_one_dish", "meal_detail_popup")
    rec = _Rec(status="failed", fail_reason="启动超时",
               trace_url="https://x/traces/20260804_f/")
    hits = build_hits([rec], work_log_dir=str(tmp_path), **_KW)
    assert len(hits) == 1
    assert hits[0].alert_type == "T2"
    assert "美团·加菜" in hits[0].stuck_point
    assert "卡在" not in hits[0].reason


def test_max_trace_reads_zero_skips_trace(tmp_path):
    for i in range(18):
        _frame(tmp_path / "20260804_z" / "meituan", i, "add_one_dish", "meal_detail_popup")
    rec = _Rec(status="cancelled", trace_url="https://x/traces/20260804_z/",
               total_ms=95000, step_count=3)
    kw = {**_KW, "max_trace_reads": 0}
    hits = build_hits([rec], work_log_dir=str(tmp_path), **kw)
    # 没读 trace → 回退保底 → deep(95s) → 深度放弃
    assert len(hits) == 1 and "深度放弃" in hits[0].reason


def test_shared_reads_budget_across_branches(tmp_path):
    # cancelled 和 failed 共用 max_trace_reads 预算;预算=1 时 cancelled 先消耗,failed 拿不到卡点
    for i in range(18):
        _frame(tmp_path / "20260804_c" / "meituan", i, "add_one_dish", "meal_detail_popup")
    for i in range(20):
        _frame(tmp_path / "20260804_d" / "meituan", i, "add_one_dish", "meal_detail_popup")
    cancelled = _Rec(status="cancelled", trace_url="https://x/traces/20260804_c/",
                     total_ms=5000, step_count=3)
    failed = _Rec(status="failed", fail_reason="启动超时",
                  trace_url="https://x/traces/20260804_d/")
    kw = {**_KW, "max_trace_reads": 1}
    hits = build_hits([cancelled, failed], work_log_dir=str(tmp_path), **kw)
    assert len(hits) == 2
    # cancelled 消耗了唯一预算 → 报卡死，卡点在 stuck_point
    assert hits[0].alert_type == "T5" and hits[0].stuck_point is not None
    # failed 超预算 → 仍报 T2,但 stuck_point 为 None
    assert hits[1].alert_type == "T2" and hits[1].stuck_point is None


# ---- _fmt_stuck 单测 ----

def test_fmt_stuck_with_ms():
    sp = StuckPoint(platform="meituan", pipeline_step="add_one_dish", frames=110, stuck_ms=32000)
    assert _fmt_stuck(sp) == "美团·加菜 110帧/32s"


def test_fmt_stuck_without_ms():
    sp = StuckPoint(platform="meituan", pipeline_step="add_one_dish", frames=110, stuck_ms=None)
    assert _fmt_stuck(sp) == "美团·加菜 110帧"