polymarket-bot/tests/test_sharpe_gate.py

"""
Tests for the real Sharpe ratio with minimum-sample gate.

Regression: sharpe_ratio was hardcoded to 0.0 in MetricsTracker and exposed
as `latest.get("sharpe_ratio") or 0` in /api/summary, and promotion_ready
could in principle flip on a statistically meaningless sample (e.g. 1
resolved trade over ~40 days of flat PnL plus a single +299 jump).

Fix: bot/metrics/sharpe.py computes an annualized Sharpe from the daily
total_pnl close series, gated to None ("insufficient_sample") below 30 days
observed / 10 resolved trades. /api/summary exposes the value plus an
explanation (sharpe_status, days_observed, min_* fields), and
promotion_ready additionally requires the sample minimums and non-null
metrics.
"""
import asyncio
from statistics import mean, stdev

import pytest

import api.main as api_main
from bot.metrics.sharpe import (
    MIN_DAYS_OBSERVED,
    MIN_RESOLVED_TRADES,
    SHARPE_INSUFFICIENT,
    SHARPE_OK,
    SHARPE_ZERO_VARIANCE,
    compute_sharpe,
    daily_returns,
    sharpe_with_gate,
)
from bot.metrics.tracker import MetricsTracker


BANKROLL = 10_000.0


def _closes_from_deltas(deltas: list[float], start: float = 0.0) -> list[float]:
    closes = [start]
    for d in deltas:
        closes.append(closes[-1] + d)
    return closes


# ── Pure computation ─────────────────────────────────────────────────────────

def test_daily_returns_are_bankroll_normalized_deltas():
    closes = [0.0, 100.0, 50.0, 50.0]
    assert daily_returns(closes, BANKROLL) == pytest.approx([0.01, -0.005, 0.0])


def test_compute_sharpe_matches_manual_formula():
    deltas = [10.0, 14.0, 8.0, 12.0, 6.0, 13.0, 9.0]
    closes = _closes_from_deltas(deltas)
    rets = [d / BANKROLL for d in deltas]
    expected = mean(rets) / stdev(rets) * 365 ** 0.5
    assert compute_sharpe(closes, BANKROLL) == pytest.approx(expected)
    assert compute_sharpe(closes, BANKROLL) > 0


def test_compute_sharpe_undefined_cases_return_none():
    assert compute_sharpe([], BANKROLL) is None
    assert compute_sharpe([0.0], BANKROLL) is None
    assert compute_sharpe([0.0, 50.0], BANKROLL) is None      # only 1 return
    assert compute_sharpe([0.0] * 40, BANKROLL) is None        # zero variance


# ── Minimum-sample gate ───────────────────────────────────────────────────────

def test_gate_blocks_current_situation_one_resolved_trade():
    """~40 flat days plus a single +299 jump, 1 resolved trade → no Sharpe."""
    closes = [0.0] * 35 + [299.06] * 5
    sharpe, status = sharpe_with_gate(closes, BANKROLL, resolved_count=1)
    assert sharpe is None
    assert status == SHARPE_INSUFFICIENT
    # The raw (ungated) value would exist and be wildly misleading:
    assert compute_sharpe(closes, BANKROLL) is not None


def test_gate_blocks_too_few_days_even_with_enough_resolved():
    closes = _closes_from_deltas([10.0, -5.0] * 10)  # 21 days < 30
    sharpe, status = sharpe_with_gate(closes, BANKROLL, resolved_count=15)
    assert sharpe is None
    assert status == SHARPE_INSUFFICIENT


def test_gate_passes_with_sufficient_sample():
    deltas = [10.0, 14.0, 8.0, 12.0, 6.0] * 8  # 40 returns → 41 days
    closes = _closes_from_deltas(deltas)
    sharpe, status = sharpe_with_gate(closes, BANKROLL, resolved_count=MIN_RESOLVED_TRADES)
    assert status == SHARPE_OK
    assert sharpe == pytest.approx(compute_sharpe(closes, BANKROLL))


def test_gate_flat_curve_with_sufficient_sample_is_zero_variance():
    sharpe, status = sharpe_with_gate([0.0] * 40, BANKROLL, resolved_count=12)
    assert sharpe is None
    assert status == SHARPE_ZERO_VARIANCE


# ── /api/summary ─────────────────────────────────────────────────────────────

class FakeDB:
    def __init__(self, daily_closes, resolved_count, total_trades=60,
                 win_rate=0.6, calibration=0.8):
        self._closes = daily_closes
        self._resolved = resolved_count
        self._total = total_trades
        self._win_rate = win_rate
        self._calibration = calibration

    async def get_metrics_history(self, days=1):
        return [{
            "win_rate": self._win_rate,
            "calibration_score": self._calibration,
            "unrealized_pnl_est": 0.0,
            "realized_pnl": 299.06,
            "total_pnl": 299.06,
        }]

    async def compute_metrics_from_db(self):
        return {
            "total_trades": self._total,
            "open_count": self._total - self._resolved,
            "closed_count": self._resolved,
            "resolved_count": self._resolved,
        }

    async def get_open_position_data(self):
        return {}, 0.0

    async def get_recently_closed_inverted(self, hours=24):
        return set()

    async def get_legacy_incomplete_count(self):
        return 0

    async def get_daily_pnl_closes(self):
        return list(self._closes)


def _summary(db, monkeypatch) -> dict:
    monkeypatch.setattr(api_main, "db", db)
    monkeypatch.delenv("PAPER_BANKROLL", raising=False)
    return asyncio.run(api_main.get_summary())


def test_api_insufficient_sample_returns_null_with_explanation(monkeypatch):
    """Current prod situation: 1 resolved, ~40 days → null Sharpe, not ready."""
    db = FakeDB(daily_closes=[0.0] * 35 + [299.06] * 5, resolved_count=1)
    s = _summary(db, monkeypatch)
    assert s["sharpe_ratio"] is None
    assert s["sharpe_status"] == SHARPE_INSUFFICIENT
    assert s["resolved_count"] == 1
    assert s["min_resolved_required"] == MIN_RESOLVED_TRADES == 10
    assert s["days_observed"] == 40
    assert s["min_days_required"] == MIN_DAYS_OBSERVED == 30
    # One lucky resolved trade must never promote, even with perfect
    # win_rate/calibration and 50+ trades.
    assert s["promotion_ready"] is False


def test_api_sharpe_appears_with_sufficient_sample(monkeypatch):
    deltas = [10.0, 14.0, 8.0, 12.0, 6.0] * 8
    db = FakeDB(daily_closes=_closes_from_deltas(deltas), resolved_count=12)
    s = _summary(db, monkeypatch)
    assert s["sharpe_status"] == SHARPE_OK
    assert s["sharpe_ratio"] == pytest.approx(
        compute_sharpe(_closes_from_deltas(deltas), BANKROLL)
    )
    assert s["sharpe_ratio"] >= 0.5
    assert s["promotion_ready"] is True


def test_api_not_ready_when_sharpe_below_threshold(monkeypatch):
    # Zero-drift curve: mean return ~0 → Sharpe ≈ 0 < 0.5
    deltas = [50.0, -50.0] * 20
    db = FakeDB(daily_closes=_closes_from_deltas(deltas), resolved_count=12)
    s = _summary(db, monkeypatch)
    assert s["sharpe_status"] == SHARPE_OK
    assert s["sharpe_ratio"] < 0.5
    assert s["promotion_ready"] is False


def test_api_not_ready_when_metrics_null(monkeypatch):
    db = FakeDB(
        daily_closes=_closes_from_deltas([10.0, 14.0, 8.0, 12.0, 6.0] * 8),
        resolved_count=12,
        win_rate=None,
        calibration=None,
    )
    s = _summary(db, monkeypatch)
    assert s["sharpe_status"] == SHARPE_OK
    assert s["promotion_ready"] is False


# ── MetricsTracker: no hardcoded 0.0 in the snapshot ─────────────────────────

class FakeTrackerDB:
    def __init__(self, daily_closes, resolved_count):
        self._closes = daily_closes
        self._resolved = resolved_count
        self.saved = None

    async def compute_metrics_from_db(self):
        return {
            "total_trades": 60,
            "open_count": 40,
            "closed_count": 20,
            "resolved_count": self._resolved,
            "wins_realized": self._resolved,
            "unrealized_pnl_est": 0.0,
            "realized_pnl": 100.0,
            "total_deployed": 1000.0,
            "total_fees": 20.0,
            "calibration_score": 0.8,
        }

    async def get_daily_pnl_closes(self):
        return list(self._closes)

    async def save_daily_metrics(self, metrics):
        self.saved = metrics


def test_tracker_stores_null_sharpe_below_gate(monkeypatch):
    monkeypatch.delenv("PAPER_BANKROLL", raising=False)
    db = FakeTrackerDB(daily_closes=[0.0] * 35 + [299.06] * 5, resolved_count=1)
    asyncio.run(MetricsTracker(db).update_daily_summary())
    assert db.saved is not None
    assert db.saved["sharpe_ratio"] is None


def test_tracker_stores_real_sharpe_above_gate(monkeypatch):
    monkeypatch.delenv("PAPER_BANKROLL", raising=False)
    closes = _closes_from_deltas([10.0, 14.0, 8.0, 12.0, 6.0] * 8)
    db = FakeTrackerDB(daily_closes=closes, resolved_count=12)
    asyncio.run(MetricsTracker(db).update_daily_summary())
    assert db.saved["sharpe_ratio"] == pytest.approx(
        compute_sharpe(closes, BANKROLL)
    )
    assert db.saved["sharpe_ratio"] != 0.0