fix(estimator): clamp expected_sold <= asking (ratio cap 1.0) -- smoke 3к exp_sold>asking

tradein-mvp/backend/app/core/config.py

@@ -119,6 +119,17 @@ class Settings(BaseSettings):
     # ENV: ESTIMATE_RADIUS_FLOOR_ENABLED, ESTIMATE_RADIUS_FLOOR_FACTOR.
     estimate_radius_floor_enabled: bool = True
     estimate_radius_floor_factor: float = 0.8
+    # Шаг 5 — clamp expected_sold <= asking: ratio > 1.0 физически невозможен для
+    # trade-in (ожидаемая цена сделки не должна превышать цену объявления).
+    # Диагноз: в high-price tier asking->sold ratio > 1.0 (product artefact, не реальные
+    # сделки выше прайса) -> expected_sold = headline x ratio > headline.
+    # При флаге True: если ratio > 1.0 — клампаем до 1.0 и логируем. Применяется
+    # к point И range (expected_sold_low/high/price) консистентно.
+    # False -> старое поведение без clamp (backward-compat).
+    # ENV: ESTIMATE_EXPECTED_SOLD_LE_ASKING.
+    estimate_expected_sold_le_asking: bool = Field(
+        default=True, validation_alias="ESTIMATE_EXPECTED_SOLD_LE_ASKING"
+    )
     # Шаг 2 — ужесточённый MAD-clip на малых выборках в same-building anchor:
     # при n < small_n_threshold используем mad_k_small вместо estimate_sb_mad_k
     # (3.5 слишком мягкий при n=7 → элитные хвосты не срезаются, mean тянется вверх).

tradein-mvp/backend/app/services/estimator.py

@@ -2861,10 +2861,22 @@ async def estimate_quality(
             ratio_basis = None
 
     if asking_to_sold_ratio is not None and median_price > 0:
-        expected_sold_per_m2 = round(median_ppm2 * asking_to_sold_ratio)
-        expected_sold_price = round(median_price * asking_to_sold_ratio)
-        expected_sold_range_low = round(range_low * asking_to_sold_ratio)
-        expected_sold_range_high = round(range_high * asking_to_sold_ratio)
+        # FIX(expected_sold-le-asking): clamp ratio <= 1.0 чтобы expected_sold не
+        # превышала объявление. Smoke: 3к/27.0М -> expected_sold 31.4М > asking.
+        # Причина: high-price tier ratio > 1.0 (product artefact, не реальные сделки
+        # выше прайса). Флаг OFF -> старое поведение без clamp.
+        effective_ratio = asking_to_sold_ratio
+        if settings.estimate_expected_sold_le_asking and effective_ratio > 1.0:
+            logger.info(
+                "expected_sold ratio clamped %.3f->1.0 (rooms=%s)",
+                effective_ratio,
+                payload.rooms,
+            )
+            effective_ratio = 1.0
+        expected_sold_per_m2 = round(median_ppm2 * effective_ratio)
+        expected_sold_price = round(median_price * effective_ratio)
+        expected_sold_range_low = round(range_low * effective_ratio)
+        expected_sold_range_high = round(range_high * effective_ratio)
 
     # ── #652: ДКП-коридор реальных сделок (ADVISORY + soft sanity-bound) ─────
     # dkp_raw уже зафетчен выше (#1795) — переиспользуем, не фетчим повторно.

tradein-mvp/backend/tests/test_estimator_expected_sold_clamp.py

@@ -0,0 +1,181 @@
+"""Tests for Fix 4: clamp expected_sold <= asking (ratio cap 1.0).
+
+Smoke-диагноз: 3к/27.0М -> expected_sold 31.4М > asking.
+Причина: _get_asking_sold_ratio для high-price tier возвращает ratio > 1.0
+(product artefact) -> expected_sold = headline x ratio > headline.
+
+Проверяем:
+1. ratio=1.15 + флаг on -> expected_sold == headline (не выше); лог clamp.
+2. ratio=0.8 -> expected_sold = headline x 0.8 (норм, без clamp).
+3. ratio None -> expected_sold не выводится (graceful).
+4. Флаг off + ratio > 1 -> expected_sold > headline (старое поведение).
+"""
+
+from __future__ import annotations
+
+import logging
+import os
+from datetime import UTC, datetime
+from typing import Any
+from unittest.mock import AsyncMock, MagicMock, patch
+
+import anyio
+import pytest
+
+os.environ.setdefault("DATABASE_URL", "postgresql+psycopg://test:test@localhost:5432/test")
+
+
+def _make_listing(*, price_per_m2: float, area_m2: float = 50.0) -> dict[str, Any]:
+    return {
+        "source": "cian",
+        "source_url": "https://cian.ru/offer/1",
+        "address": "ЕКБ, ул. Малышева, 30",
+        "lat": 56.838,
+        "lon": 60.595,
+        "rooms": 3,
+        "area_m2": area_m2,
+        "floor": 10,
+        "total_floors": 20,
+        "price_rub": price_per_m2 * area_m2,
+        "price_per_m2": price_per_m2,
+        "listing_date": datetime(2026, 5, 1),
+        "days_on_market": 5,
+        "photo_urls": [],
+        "scraped_at": datetime(2026, 5, 20, tzinfo=UTC),
+        "distance_m": 100.0,
+        "relevance_score": 0.1,
+    }
+
+
+_ANALOGS: list[dict[str, Any]] = [
+    _make_listing(price_per_m2=260_000.0),
+    _make_listing(price_per_m2=270_000.0),
+    _make_listing(price_per_m2=280_000.0),
+]
+
+
+def _make_geo():
+    from app.services.geocoder import GeocodeResult
+
+    return GeocodeResult(
+        lat=56.838,
+        lon=60.595,
+        full_address="Свердловская обл., Екатеринбург, ул. Малышева, 30",
+        provider="nominatim",
+    )
+
+
+def _make_payload(rooms: int = 3):
+    from app.schemas.trade_in import TradeInEstimateInput
+
+    return TradeInEstimateInput(
+        address="ЕКБ, ул. Малышева, 30", area_m2=50.0, rooms=rooms, floor=10, total_floors=20
+    )
+
+
+def _run_estimate(
+    ratio_tuple: tuple[float | None, str | None],
+    *,
+    clamp_enabled: bool = True,
+) -> Any:
+    from app.services.estimator import estimate_quality
+
+    db = MagicMock()
+    payload = _make_payload()
+
+    async def _run() -> Any:
+        with (
+            patch("app.core.config.settings.estimate_expected_sold_le_asking", new=clamp_enabled),
+            patch("app.services.estimator.geocode", new=AsyncMock(return_value=_make_geo())),
+            patch("app.services.estimator.dadata_clean_address", new=AsyncMock(return_value=None)),
+            patch("app.services.estimator.match_house_readonly", return_value=None),
+            patch(
+                "app.services.estimator.get_house_metadata",
+                new=AsyncMock(return_value=None),
+            ),
+            patch(
+                "app.services.estimator._fetch_analogs",
+                return_value=(list(_ANALOGS), False, "S"),
+            ),
+            patch("app.services.estimator._fetch_deals", return_value=[]),
+            patch(
+                "app.services.estimator._get_or_fetch_imv_cached",
+                new=AsyncMock(return_value=None),
+            ),
+            patch(
+                "app.services.estimator._get_or_fetch_yandex_valuation_cached",
+                new=AsyncMock(return_value=None),
+            ),
+            patch(
+                "app.services.estimator.estimate_via_cian_valuation",
+                new=AsyncMock(return_value=None),
+            ),
+            patch("app.services.estimator._fetch_dkp_corridor", return_value=None),
+            patch("app.services.estimator._get_asking_sold_ratio", return_value=ratio_tuple),
+        ):
+            return await estimate_quality(payload, db)
+
+    return anyio.run(_run)
+
+
+def test_expected_sold_clamped_to_headline_when_ratio_above_1(
+    caplog: pytest.LogCaptureFixture,
+) -> None:
+    ratio = 1.15
+    with caplog.at_level(logging.INFO, logger="app.services.estimator"):
+        est = _run_estimate((ratio, "per_rooms"), clamp_enabled=True)
+    assert est.median_price_rub > 0, "headline должен быть задан аналогами"
+    assert est.expected_sold_price_rub is not None
+    assert (
+        est.expected_sold_price_rub <= est.median_price_rub
+    ), f"expected_sold {est.expected_sold_price_rub} > asking {est.median_price_rub}"
+    assert est.expected_sold_per_m2 is not None
+    assert (
+        est.expected_sold_per_m2 <= est.median_price_per_m2
+    ), "expected_sold_per_m2 превышает median_price_per_m2"
+    assert est.expected_sold_range_high_rub is not None
+    assert (
+        est.expected_sold_range_high_rub <= est.range_high_rub
+    ), "expected_sold_range_high > range_high"
+    assert est.expected_sold_range_low_rub is not None
+    assert (
+        est.expected_sold_range_low_rub <= est.range_low_rub
+    ), "expected_sold_range_low > range_low"
+    assert est.expected_sold_price_rub == est.median_price_rub
+    assert est.expected_sold_per_m2 == est.median_price_per_m2
+    clamp_logs = [r for r in caplog.records if "clamped" in r.getMessage()]
+    assert clamp_logs, "Ожидался log-message о clamp ratio"
+    assert "1.150" in clamp_logs[0].getMessage() or "1.15" in clamp_logs[0].getMessage()
+
+
+def test_expected_sold_not_clamped_when_ratio_below_1() -> None:
+    ratio = 0.8
+    est = _run_estimate((ratio, "per_rooms"), clamp_enabled=True)
+    assert est.median_price_rub > 0
+    assert est.expected_sold_price_rub == round(est.median_price_rub * ratio)
+    assert est.expected_sold_per_m2 == round(est.median_price_per_m2 * ratio)
+    assert est.expected_sold_range_low_rub == round(est.range_low_rub * ratio)
+    assert est.expected_sold_range_high_rub == round(est.range_high_rub * ratio)
+    assert est.expected_sold_price_rub < est.median_price_rub
+
+
+def test_expected_sold_none_when_ratio_none() -> None:
+    est = _run_estimate((None, None), clamp_enabled=True)
+    assert est.expected_sold_price_rub is None
+    assert est.expected_sold_per_m2 is None
+    assert est.expected_sold_range_low_rub is None
+    assert est.expected_sold_range_high_rub is None
+    assert est.asking_to_sold_ratio is None
+    assert est.median_price_rub > 0
+
+
+def test_expected_sold_exceeds_asking_when_clamp_flag_off() -> None:
+    ratio = 1.15
+    est = _run_estimate((ratio, "per_rooms"), clamp_enabled=False)
+    assert est.median_price_rub > 0
+    assert est.expected_sold_price_rub is not None
+    assert est.expected_sold_price_rub > est.median_price_rub, (
+        f"Ожидалось expected_sold > asking при clamp=False, "
+        f"но {est.expected_sold_price_rub} <= {est.median_price_rub}"
+    )
+    assert est.expected_sold_price_rub == round(est.median_price_rub * ratio)