feat(metrics): real Sharpe ratio from daily PnL curve with minimum-sample gate

sharpe_ratio was hardcoded to 0.0 in MetricsTracker and exposed as
'or 0' in /api/summary. With only 1 resolved trade (~40 flat days plus
one +299 jump) any computed Sharpe is statistically meaningless, so:

- bot/metrics/sharpe.py: annualized Sharpe (sqrt(365)) from daily
  total_pnl closes, normalized by bankroll; sharpe_with_gate() returns
  None + status until >=30 days observed AND >=10 resolved trades.
- Database.get_daily_pnl_closes(): last metrics_daily snapshot per UTC
  day, oldest first — the return series input.
- MetricsTracker: stores the real (gated) Sharpe in the snapshot, NULL
  below the gate; log line now includes sharpe.
- /api/summary: live Sharpe + sharpe_status/days_observed/min_* fields
  explaining why it is null; resolved_count now live from COUNT(*).
- promotion_ready: requires resolved>=10, days>=30, and non-null
  win_rate/calibration/sharpe plus existing thresholds — a single lucky
  resolved trade can no longer promote.
- Dashboard Sharpe card shows the insufficient-sample explanation when
  null instead of a bare em dash.

Tests: 13 new in tests/test_sharpe_gate.py (formula, gate, API contract,
tracker snapshot); verified failing pre-fix. Suite: 62 passed.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

bot/data/db.py

@@ -348,6 +348,24 @@ class Database:
             )
             return [dict(r) for r in rows]
 
+    async def get_daily_pnl_closes(self) -> list[float]:
+        """Return the closing total_pnl of every observed UTC day, oldest first.
+
+        One value per calendar day with at least one metrics_daily snapshot
+        (the day's last snapshot, same collapse rule as get_metrics_history).
+        This is the input series for the Sharpe ratio: len() = days observed,
+        consecutive deltas = daily PnL changes.
+        """
+        async with self._pool.acquire() as conn:
+            rows = await conn.fetch(
+                """
+                SELECT DISTINCT ON (timestamp::date) total_pnl
+                FROM metrics_daily
+                ORDER BY timestamp::date ASC, timestamp DESC
+                """
+            )
+            return [float(r["total_pnl"] or 0) for r in rows]
+
     async def backfill_feature_columns(self) -> int:
         """Back-populate feat_*_lo for trades created before Phase 6.
 

bot/metrics/sharpe.py

@@ -0,0 +1,79 @@
+"""
+Sharpe ratio from the paper portfolio's daily PnL curve, with a minimum-sample gate.
+
+The input series is the closing total_pnl of each observed UTC day
+(Database.get_daily_pnl_closes). Daily returns are PnL deltas normalized by
+the paper bankroll:
+
+    r_t = (pnl_t − pnl_{t−1}) / bankroll
+
+Sharpe = mean(r) / sample_std(r) × √365, annualized — prediction markets
+resolve every calendar day, so 365 is used instead of 252 trading days.
+Risk-free rate is taken as 0.
+
+Gate: with a tiny sample (e.g. 1 resolved trade over a flat curve plus one
++299 jump) any Sharpe value is statistically meaningless — artificially huge
+or tiny depending on where the jump lands. So no numeric Sharpe is exposed
+until BOTH minimums are met:
+
+    days observed     >= MIN_DAYS_OBSERVED   (30)
+    resolved trades   >= MIN_RESOLVED_TRADES (10)
+
+Below either minimum the value is None with status "insufficient_sample".
+A perfectly flat curve (zero variance) also yields None ("zero_variance"):
+Sharpe is undefined there, not infinite.
+"""
+from statistics import mean, stdev
+from typing import Optional
+
+MIN_DAYS_OBSERVED = 30
+MIN_RESOLVED_TRADES = 10
+ANNUALIZATION_DAYS = 365
+
+SHARPE_OK = "ok"
+SHARPE_INSUFFICIENT = "insufficient_sample"
+SHARPE_ZERO_VARIANCE = "zero_variance"
+
+
+def daily_returns(daily_pnl_closes: list[float], bankroll: float) -> list[float]:
+    """Bankroll-normalized day-over-day returns from a daily PnL-close series."""
+    return [
+        (curr - prev) / bankroll
+        for prev, curr in zip(daily_pnl_closes, daily_pnl_closes[1:])
+    ]
+
+
+def compute_sharpe(daily_pnl_closes: list[float], bankroll: float) -> Optional[float]:
+    """Annualized Sharpe of the daily PnL curve, or None if undefined.
+
+    None when there are fewer than 2 returns (need 3+ daily closes) or the
+    return series has zero variance. No sample-size gate here — see
+    sharpe_with_gate() for the exposed value.
+    """
+    returns = daily_returns(daily_pnl_closes, bankroll)
+    if len(returns) < 2:
+        return None
+    sd = stdev(returns)
+    if sd == 0:
+        return None
+    return mean(returns) / sd * ANNUALIZATION_DAYS ** 0.5
+
+
+def sharpe_with_gate(
+    daily_pnl_closes: list[float],
+    bankroll: float,
+    resolved_count: int,
+) -> tuple[Optional[float], str]:
+    """Return (sharpe, status) applying the minimum-sample gate.
+
+    status: "ok"                  — sharpe is a meaningful float
+            "insufficient_sample" — sample below minimums, sharpe is None
+            "zero_variance"       — sample OK but flat curve, sharpe is None
+    """
+    days_observed = len(daily_pnl_closes)
+    if days_observed < MIN_DAYS_OBSERVED or resolved_count < MIN_RESOLVED_TRADES:
+        return None, SHARPE_INSUFFICIENT
+    sharpe = compute_sharpe(daily_pnl_closes, bankroll)
+    if sharpe is None:
+        return None, SHARPE_ZERO_VARIANCE
+    return sharpe, SHARPE_OK

bot/metrics/tracker.py

@@ -15,12 +15,16 @@ win_rate            Fraction of resolved closed trades with close_pnl > 0.
                     NULL if fewer than 5 resolved trades.
 calibration_score   1 − AVG((final_prob − resolution)²) on resolved trades.
                     Brier score (higher = better calibration). NULL if < 10 resolved.
-sharpe_ratio        0.0 — requires a daily-return time series, not yet tracked.
+sharpe_ratio        Annualized Sharpe of the daily total_pnl curve (see
+                    bot/metrics/sharpe.py). NULL until the sample gate passes:
+                    >= 30 days observed AND >= 10 resolved trades.
 """
 import logging
+import os
 from datetime import datetime, UTC
 
 from bot.data.db import Database
+from bot.metrics.sharpe import sharpe_with_gate
 
 log = logging.getLogger(__name__)
 
@@ -61,6 +65,12 @@ class MetricsTracker:
 
         avg_edge = total_pnl / total_deployed if total_deployed > 0 else 0.0
 
+        # Sharpe: real value from the daily PnL curve, NULL while the sample
+        # gate (>=30 days observed, >=10 resolved) is not met.
+        bankroll = float(os.getenv("PAPER_BANKROLL", "10000"))
+        daily_closes = await self._db.get_daily_pnl_closes()
+        sharpe, sharpe_status = sharpe_with_gate(daily_closes, bankroll, resolved)
+
         metrics = {
             "timestamp":          datetime.now(UTC),
             "total_trades":       int(raw["total_trades"]),
@@ -74,7 +84,7 @@ class MetricsTracker:
             "total_pnl":          total_pnl,
             "win_rate":           win_rate,
             "avg_edge":           avg_edge,
-            "sharpe_ratio":       0.0,   # requires daily-return series (not yet tracked)
+            "sharpe_ratio":       sharpe,   # NULL until sample gate passes
             "calibration_score":  calibration,
             "paper_mode":         True,
         }
@@ -83,9 +93,10 @@ class MetricsTracker:
         log.info(
             "Daily metrics | trades=%d (open=%d closed=%d resolved=%d) | "
             "unrealized=$%.2f realized=$%.2f total=$%.2f | "
-            "win_rate=%s calibration=%s",
+            "win_rate=%s calibration=%s sharpe=%s",
             metrics["total_trades"], open_count, closed_count, resolved,
             unrealized, realized, total_pnl,
             f"{win_rate:.1%}" if win_rate is not None else "n/a (<5)",
             f"{calibration:.3f}" if calibration is not None else "n/a (<10)",
+            f"{sharpe:.2f}" if sharpe is not None else f"n/a ({sharpe_status})",
         )