feat(ga): fitness continua v1 con tanh(sharpe) + penalita' moltiplicativa di drawdown

Phase 1 v0 usava `max(0, dsr - 0.5*max_dd)` che azzerava brutalmente la fitness
quando max_dd > 2*dsr. Real run v4 aveva 55/55 strategie a fitness=0 (DSR ~0.001,
max_dd > 0.5), zero pressione selettiva sul GA.

v1: base = 0.5*dsr + 0.5*0.5*(tanh(sharpe)+1) in [0,1], modulata da penalty
moltiplicativa 1/(1+k*max_dd) in (0,1]. Hard kill (no-trade, HIGH adversarial)
preservati. Fitness sempre >0 per strategie con almeno 1 trade -> il GA
puo' preferire "meno cattivo" a "catastrofico" anche su sharpe negativo.

Tests: +3 nuovi (continuous mediocre, bounded, monotonic drawdown), 4 esistenti
restano verdi. Suite 138 -> 141 passed. ruff + mypy strict puliti.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

src/multi_swarm/ga/fitness.py

@@ -1,17 +1,31 @@
-"""Fitness function v0 della Phase 1.
+"""Fitness function v1 della Phase 1.
 
 Combina :class:`FalsificationReport` (metriche di robustezza) e
 :class:`AdversarialReport` (findings euristici) in uno scalare ``>= 0`` che il
 GA usa per selezione e ranking.
 
-Logica deliberatamente coarse: DSR penalizzato dal max drawdown, con due
-kill-switch hard (no-trade, finding HIGH adversarial) che azzerano la fitness.
-La penalita' lineare sul drawdown e' un compromesso volutamente semplice;
-versioni successive potranno usare Calmar o utility convessa.
+Versione v1: rispetto alla v0 (DSR meno penalita' lineare di drawdown, clamp
+a zero) la formula e' continua e quasi sempre strettamente positiva, in modo
+da fornire un gradient anche su strategie mediocri o con Sharpe negativo.
+Restano due kill-switch hard (no-trade, finding HIGH adversarial) che azzerano
+la fitness.
+
+Formula::
+
+    sharpe_norm = 0.5 * (tanh(sharpe) + 1.0)              # in [0, 1]
+    base        = dsr_weight * dsr + sharpe_weight * sharpe_norm
+    penalty     = 1.0 / (1.0 + drawdown_penalty * max_drawdown)
+    fitness     = max(0.0, base * penalty)
+
+Con i default ``dsr_weight = sharpe_weight = 0.5`` la base e' in ``[0, 1]`` e
+``penalty`` in ``(0, 1]``: fitness e' bounded in ``[0, 1]`` per input sani e
+mai esattamente zero finche' Sharpe e' finito e ``max_dd`` finito.
 """
 
 from __future__ import annotations
 
+import math
+
 from ..agents.adversarial import AdversarialReport, Severity
 from ..agents.falsification import FalsificationReport
 
@@ -19,26 +33,39 @@ from ..agents.falsification import FalsificationReport
 def compute_fitness(
     falsification: FalsificationReport,
     adversarial: AdversarialReport,
-    drawdown_penalty: float = 0.5,
+    drawdown_penalty: float = 1.0,
+    dsr_weight: float = 0.5,
+    sharpe_weight: float = 0.5,
 ) -> float:
-    """Calcola la fitness scalare di una strategia.
+    """Calcola la fitness scalare di una strategia (v1, continua).
 
     Args:
-        falsification: report con DSR, max_drawdown, n_trades.
+        falsification: report con DSR, Sharpe, max_drawdown, n_trades.
         adversarial: report con eventuali findings euristici.
-        drawdown_penalty: peso lineare sul max drawdown (default 0.5).
+        drawdown_penalty: peso del max drawdown nel denominatore della
+            penalita' moltiplicativa (default 1.0). Valori piu' alti
+            penalizzano piu' severamente strategie con DD alto.
+        dsr_weight: peso del DSR nella base (default 0.5).
+        sharpe_weight: peso dello Sharpe normalizzato nella base
+            (default 0.5).
 
     Returns:
-        Fitness ``>= 0``. Zero indica strategia da scartare.
+        Fitness ``>= 0``. Zero indica strategia da scartare (no-trade o
+        kill adversarial). Valori tipici per strategie sane: ``[0.05, 1.0]``.
 
     Logica:
         1. ``n_trades == 0`` → 0 (nessuna evidenza, sega subito).
         2. Almeno un finding ``HIGH`` adversarial → 0 (kill).
-        3. Altrimenti: ``dsr - drawdown_penalty * max_drawdown``, clamped a 0.
+        3. Altrimenti combina DSR e ``tanh(sharpe)`` normalizzato in
+           ``[0, 1]``, modulato da una penalita' continua del drawdown
+           ``1 / (1 + k * max_dd)``.
     """
     if falsification.n_trades == 0:
         return 0.0
     if any(f.severity == Severity.HIGH for f in adversarial.findings):
         return 0.0
-    raw = falsification.dsr - drawdown_penalty * falsification.max_drawdown
-    return max(0.0, float(raw))
+    dsr = max(0.0, min(1.0, float(falsification.dsr)))
+    sharpe_norm = 0.5 * (math.tanh(float(falsification.sharpe)) + 1.0)
+    base = dsr_weight * dsr + sharpe_weight * sharpe_norm
+    penalty = 1.0 / (1.0 + drawdown_penalty * float(falsification.max_drawdown))
+    return max(0.0, float(base * penalty))

tests/unit/test_fitness.py

@@ -1,13 +1,18 @@
+from itertools import pairwise
+
 from multi_swarm.agents.adversarial import AdversarialReport, Finding, Severity
 from multi_swarm.agents.falsification import FalsificationReport
 from multi_swarm.ga.fitness import compute_fitness
 
 
 def make_falsification(
-    dsr: float = 0.7, max_dd: float = 0.2, n_trades: int = 30
+    dsr: float = 0.7,
+    max_dd: float = 0.2,
+    n_trades: int = 30,
+    sharpe: float = 1.5,
 ) -> FalsificationReport:
     return FalsificationReport(
-        sharpe=1.5,
+        sharpe=sharpe,
         dsr=dsr,
         dsr_pvalue=0.05,
         max_drawdown=max_dd,
@@ -43,3 +48,44 @@ def test_fitness_zeroed_by_high_severity_finding() -> None:
         findings=[Finding(name="degenerate", severity=Severity.HIGH, detail="x")]
     )
     assert compute_fitness(f, a) == 0.0
+
+
+def test_fitness_continuous_signal_for_mediocre() -> None:
+    """Strategie mediocri (DSR ~0, Sharpe negativo) hanno comunque fitness>0
+    e la meno cattiva e' preferita."""
+    a = AdversarialReport()
+    less_bad = make_falsification(dsr=0.001, sharpe=-0.5, max_dd=0.3)
+    worse = make_falsification(dsr=0.001, sharpe=-2.0, max_dd=0.3)
+    f_less = compute_fitness(less_bad, a)
+    f_worse = compute_fitness(worse, a)
+    assert f_less > 0.0
+    assert f_worse > 0.0
+    assert f_less > f_worse
+
+
+def test_fitness_bounded() -> None:
+    """Fitness e' bounded in [0, 2.0] per input tipici."""
+    a = AdversarialReport()
+    cases = [
+        make_falsification(dsr=0.0, sharpe=-5.0, max_dd=0.0),
+        make_falsification(dsr=0.0, sharpe=0.0, max_dd=0.0),
+        make_falsification(dsr=0.5, sharpe=1.0, max_dd=0.2),
+        make_falsification(dsr=0.9, sharpe=2.0, max_dd=0.15),
+        make_falsification(dsr=1.0, sharpe=5.0, max_dd=0.0),
+        make_falsification(dsr=1.0, sharpe=10.0, max_dd=5.0),
+    ]
+    for f in cases:
+        v = compute_fitness(f, a)
+        assert 0.0 <= v <= 2.0, f"fitness {v} fuori range per {f}"
+
+
+def test_fitness_normalizes_drawdown() -> None:
+    """Con DSR e Sharpe fissi, fitness e' monotona decrescente in max_dd."""
+    a = AdversarialReport()
+    dds = [0.0, 0.1, 0.5, 1.0, 2.0, 5.0]
+    fitnesses = [
+        compute_fitness(make_falsification(dsr=0.5, sharpe=1.0, max_dd=dd), a)
+        for dd in dds
+    ]
+    for prev, curr in pairwise(fitnesses):
+        assert prev > curr, f"non monotona: {fitnesses}"