feat(phase-2.5): mutate_prompt_llm operator + weighted dispatcher + GA wiring

Implementazione completa Phase 2.5 (LLM prompt mutator) seguendo il piano in
docs/superpowers/plans/2026-05-11-mutate-prompt-llm-phase-2-5.md.

Nuovo modulo src/multi_swarm/genome/mutation_prompt_llm.py:
- 6 mutation instructions (tighten_threshold, swap_comparator, add_condition,
  remove_condition, change_timeframe, add_temporal_gate)
- mutate_prompt_llm(g, llm, rng, mutator_tier=ModelTier.B): clona genome con
  tier B per la call mutator, costruisce system+user prompt con istruzione
  scelta random, estrae prompt da tag <prompt>...</prompt>, valida
- is_valid_prompt(): 3 check (lunghezza >= 50, keyword tecnica, diff > 5%
  Levenshtein-like via difflib.SequenceMatcher)
- Fallback random_mutate su qualsiasi validation fail O LLM exception

Esteso src/multi_swarm/genome/mutation.py con weighted_random_mutate dispatcher:
con probabilità prompt_mutation_weight invoca mutate_prompt_llm, altrimenti
random_mutate. Backward compat: llm=None oppure weight=0 → solo scalare.

Integrazione GA loop + RunConfig:
- GAConfig.prompt_mutation_weight: float = 0.0 (default off)
- next_generation(llm=...) propagato all'invocazione mutator
- RunConfig.prompt_mutation_weight con stesso default
- run_phase1: passa llm a next_generation solo se weight > 0
- scripts/run_phase1.py: flag CLI --prompt-mutation-weight

Tests (+18, 175 totale):
- tests/unit/test_mutation_prompt_llm.py (12): extract_prompt, is_valid_prompt
  3 check, operator success + fallback su 3 modi (invalid/identical/exception),
  tier B per LLM call, istruzione scelta dal pool
- tests/unit/test_mutation_dispatcher.py (4): weight 0/1/None + distribuzione
  30/70 su 1000 estrazioni con tolleranza ±5%
- tests/integration/test_ga_loop_with_prompt_mutator.py (2): loop con
  weight=1.0 produce prompt evoluti; backward compat weight=0 invariato

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

scripts/run_phase1.py

@@ -31,6 +31,12 @@ def parse_args() -> argparse.Namespace:
     p.add_argument("--end", default="2026-01-01T00:00:00+00:00")
     p.add_argument("--fees-bp", type=float, default=5.0)
     p.add_argument("--n-trials-dsr", type=int, default=50)
+    p.add_argument(
+        "--prompt-mutation-weight",
+        type=float,
+        default=0.0,
+        help="Phase 2.5: probabilità (0-1) che la mutazione invochi LLM mutator tier B",
+    )
     return p.parse_args()
 
 
@@ -84,6 +90,7 @@ def main() -> None:
         fees_bp=args.fees_bp,
         n_trials_dsr=args.n_trials_dsr,
         db_path=settings.db_path,
+        prompt_mutation_weight=args.prompt_mutation_weight,
     )
 
     run_id = run_phase1(cfg, ohlcv=ohlcv, llm=llm)

src/multi_swarm/ga/loop.py

@@ -2,10 +2,11 @@ from __future__ import annotations
 
 import random
 from dataclasses import dataclass
+from typing import Any
 
 from ..genome.crossover import uniform_crossover
 from ..genome.hypothesis import HypothesisAgentGenome
-from ..genome.mutation import random_mutate
+from ..genome.mutation import weighted_random_mutate
 from .selection import elite_select, tournament_select
 
 
@@ -15,6 +16,7 @@ class GAConfig:
     elite_k: int
     tournament_k: int
     p_crossover: float
+    prompt_mutation_weight: float = 0.0  # Phase 2.5: opt-in LLM mutator
 
 
 def next_generation(
@@ -22,8 +24,14 @@ def next_generation(
     fitnesses: dict[str, float],
     cfg: GAConfig,
     rng: random.Random,
+    llm: Any | None = None,
 ) -> list[HypothesisAgentGenome]:
-    """Costruisce la prossima generazione: elitismo + tournament + crossover/mutate."""
+    """Costruisce la prossima generazione: elitismo + tournament + crossover/mutate.
+
+    Quando ``cfg.prompt_mutation_weight > 0`` e ``llm`` è fornito, la mutazione
+    invoca ``weighted_random_mutate`` che con quella probabilità usa
+    ``mutate_prompt_llm`` (Phase 2.5).
+    """
     new_pop: list[HypothesisAgentGenome] = list(
         elite_select(population, fitnesses, cfg.elite_k)
     )
@@ -35,7 +43,9 @@ def next_generation(
             child = uniform_crossover(p1, p2, rng)
         else:
             parent = tournament_select(population, fitnesses, cfg.tournament_k, rng)
-            child = random_mutate(parent, rng)
+            child = weighted_random_mutate(
+                parent, rng, llm=llm, prompt_mutation_weight=cfg.prompt_mutation_weight
+            )
         new_pop.append(child)
 
     return new_pop[: cfg.population_size]

src/multi_swarm/genome/mutation.py

@@ -75,3 +75,23 @@ MUTATION_OPS = (
 def random_mutate(g: HypothesisAgentGenome, rng: random.Random) -> HypothesisAgentGenome:
     op = rng.choice(MUTATION_OPS)
     return op(g, rng)
+
+
+def weighted_random_mutate(
+    g: HypothesisAgentGenome,
+    rng: random.Random,
+    llm: Any | None = None,
+    prompt_mutation_weight: float = 0.0,
+) -> HypothesisAgentGenome:
+    """Dispatcher pesato fra mutate_prompt_llm e random_mutate scalare.
+
+    Con probabilità ``prompt_mutation_weight`` invoca ``mutate_prompt_llm``,
+    altrimenti ``random_mutate``. Se ``llm`` è ``None`` o il peso è 0,
+    è equivalente a ``random_mutate`` (backward-compat).
+    """
+    if llm is not None and prompt_mutation_weight > 0 and rng.random() < prompt_mutation_weight:
+        # Import inline per evitare ciclo: mutation_prompt_llm importa da mutation.
+        from .mutation_prompt_llm import mutate_prompt_llm
+
+        return mutate_prompt_llm(g, llm, rng)
+    return random_mutate(g, rng)

src/multi_swarm/genome/mutation_prompt_llm.py

@@ -0,0 +1,167 @@
+"""Phase 2.5 operator: ``mutate_prompt_llm``.
+
+Quinto operatore di mutazione che riscrive il ``system_prompt`` di un genoma
+usando un LLM tier B come "mutator". Genera diversità prompt-level dove gli
+altri quattro operatori toccano solo i quattro parametri scalari.
+
+Fallback sicuro: se la mutazione LLM produce output invalido o troppo simile
+al parent, l'operatore degrada silenziosamente a ``random_mutate``.
+"""
+
+from __future__ import annotations
+
+import random
+import re
+from dataclasses import replace
+from difflib import SequenceMatcher
+from typing import Any, Protocol
+
+from .hypothesis import HypothesisAgentGenome, ModelTier
+from .mutation import _clone_with, random_mutate
+
+# Sei tipi di mutazione "atomiche", scelti uniformemente.
+MUTATION_INSTRUCTIONS: dict[str, str] = {
+    "tighten_threshold": (
+        "Rendi UNA soglia numerica nella strategia più restrittiva del 10-20%. "
+        "Esempio: se RSI > 70 diventa RSI > 78. Lascia tutto il resto identico."
+    ),
+    "swap_comparator": (
+        "Inverti UN comparator (gt -> lt, gte -> lte o viceversa) in una sola "
+        "condizione. Mantieni lo stesso intent generale della strategia."
+    ),
+    "add_condition": (
+        "Aggiungi UNA condizione AND a una rule esistente per renderla più "
+        "selettiva. La condizione deve usare una feature/indicator coerente con "
+        "il resto della strategia."
+    ),
+    "remove_condition": (
+        "Rimuovi UNA condizione ridondante o ovvia da una rule, semplificando la "
+        "logica senza alterarne l'intent principale."
+    ),
+    "change_timeframe": (
+        "Modifica UNA finestra rolling/lookback di +/- 20-40% (es. SMA(50) -> "
+        "SMA(70)). Solo un parametro temporale."
+    ),
+    "add_temporal_gate": (
+        "Aggiungi UN gate temporale alla strategia usando una delle feature "
+        "'hour', 'dow', 'is_weekend', 'minute_of_hour' per filtrare il "
+        "trading a specifici momenti."
+    ),
+}
+
+# Keyword tecniche minime per validare che il prompt sia ancora "una strategia".
+_VALID_KEYWORDS = (
+    "rsi", "sma", "ema", "atr", "momentum", "breakout", "mean", "reversion",
+    "macd", "vwap", "bb", "bollinger", "stoch", "trend", "signal", "buy",
+    "sell", "long", "short", "entry", "exit", "stop", "rule", "condition",
+    "if", "when", "and", "or", "gt", "lt", ">", "<", "ge", "le",
+    "hour", "dow", "weekend", "indicator", "feature",
+)
+
+_MIN_PROMPT_LENGTH = 50
+_MIN_DIFF_RATIO = 0.05  # Levenshtein-like: prompt deve essere almeno 5% diverso
+
+_MUTATOR_SYSTEM_PROMPT = (
+    "Sei un mutator evolutivo per prompt di strategie di trading algoritmico. "
+    "Ricevi un PROMPT originale e una ISTRUZIONE di mutazione atomica. "
+    "Produci una versione modificata del prompt che applica SOLO quella "
+    "mutazione, preservando intent e struttura generale. "
+    "Output: solo il nuovo prompt fra tag <prompt>...</prompt>. "
+    "Nessun preambolo, nessuna spiegazione."
+)
+
+_PROMPT_RE = re.compile(r"<prompt>\s*(.*?)\s*</prompt>", re.DOTALL | re.IGNORECASE)
+
+
+class _LLMClientLike(Protocol):
+    """Subset minimo dell'API LLMClient che usa l'operatore.
+
+    Permette di mockare l'LLM nei test senza importare la classe concreta.
+    """
+
+    def complete(
+        self,
+        genome: HypothesisAgentGenome,
+        system: str,
+        user: str,
+        max_tokens: int = ...,
+    ) -> Any: ...
+
+
+def _extract_prompt(text: str) -> str:
+    """Estrae il prompt mutato dal completion text.
+
+    Cerca tag ``<prompt>...</prompt>``. Se assenti, ritorna il testo strip.
+    """
+    m = _PROMPT_RE.search(text)
+    if m:
+        return m.group(1).strip()
+    return text.strip()
+
+
+def _string_diff_ratio(a: str, b: str) -> float:
+    """Ritorna ``1 - similarity`` (0.0 = identici, 1.0 = completamente diversi)."""
+    if not a and not b:
+        return 0.0
+    return 1.0 - SequenceMatcher(None, a, b).ratio()
+
+
+def is_valid_prompt(new_prompt: str, parent_prompt: str) -> bool:
+    """Validation gate per il prompt LLM-mutato.
+
+    Tre check:
+    1. Lunghezza minima 50 caratteri.
+    2. Contiene almeno una keyword tecnica (rsi, sma, signal, ecc).
+    3. Diversità Levenshtein-like > 5% rispetto al parent.
+    """
+    if len(new_prompt) < _MIN_PROMPT_LENGTH:
+        return False
+    lowered = new_prompt.lower()
+    if not any(kw in lowered for kw in _VALID_KEYWORDS):
+        return False
+    if _string_diff_ratio(new_prompt, parent_prompt) < _MIN_DIFF_RATIO:
+        return False
+    return True
+
+
+def mutate_prompt_llm(
+    g: HypothesisAgentGenome,
+    llm: _LLMClientLike,
+    rng: random.Random,
+    mutator_tier: ModelTier = ModelTier.B,
+    max_tokens: int = 2000,
+) -> HypothesisAgentGenome:
+    """Operatore di mutazione prompt-level via LLM mutator.
+
+    Sceglie una mutation-instruction casuale fra sei tipi, fa una chiamata
+    LLM tier B per ottenere il prompt mutato, valida l'output. Su validation
+    fail (output troppo corto, non-strategia, troppo simile al parent),
+    fallback silenzioso a ``random_mutate``.
+    """
+    instruction_key = rng.choice(list(MUTATION_INSTRUCTIONS))
+    instruction = MUTATION_INSTRUCTIONS[instruction_key]
+
+    user_prompt = (
+        f"PROMPT ORIGINALE:\n{g.system_prompt}\n\n"
+        f"ISTRUZIONE DI MUTAZIONE ({instruction_key}):\n{instruction}\n\n"
+        f"Genera la versione modificata fra tag <prompt>...</prompt>."
+    )
+
+    # Mutator usa un tier diverso (B) — clone temporaneo del genoma con tier override.
+    mutator_genome = replace(g, model_tier=mutator_tier)
+
+    try:
+        result = llm.complete(
+            mutator_genome,
+            system=_MUTATOR_SYSTEM_PROMPT,
+            user=user_prompt,
+            max_tokens=max_tokens,
+        )
+    except Exception:
+        return random_mutate(g, rng)
+
+    new_prompt = _extract_prompt(getattr(result, "text", ""))
+    if not is_valid_prompt(new_prompt, g.system_prompt):
+        return random_mutate(g, rng)
+
+    return _clone_with(g, system_prompt=new_prompt)

src/multi_swarm/orchestrator/run.py

@@ -49,6 +49,7 @@ class RunConfig:
     fees_bp: float = 5.0
     n_trials_dsr: int = 50
     db_path: Path = field(default_factory=lambda: Path("./runs.db"))
+    prompt_mutation_weight: float = 0.0  # Phase 2.5: opt-in LLM mutator
 
 
 def run_phase1(
@@ -90,6 +91,7 @@ def run_phase1(
         elite_k=cfg.elite_k,
         tournament_k=cfg.tournament_k,
         p_crossover=cfg.p_crossover,
+        prompt_mutation_weight=cfg.prompt_mutation_weight,
     )
 
     try:
@@ -173,7 +175,10 @@ def run_phase1(
             )
 
             if gen < cfg.n_generations - 1:
-                population = next_generation(population, fitnesses, ga_cfg, rng)
+                population = next_generation(
+                    population, fitnesses, ga_cfg, rng,
+                    llm=llm if cfg.prompt_mutation_weight > 0 else None,
+                )
 
         repo.complete_run(
             run_id, total_cost=repo.total_cost(run_id), status="completed"

tests/integration/test_ga_loop_with_prompt_mutator.py

@@ -0,0 +1,104 @@
+"""Integration test Phase 2.5: GA loop con LLM mutator attivo.
+
+Verifica che ``next_generation`` con ``prompt_mutation_weight > 0`` e ``llm``
+fornito produca figli con system_prompt mutato dall'LLM (e non solo scalari).
+"""
+
+from __future__ import annotations
+
+import random
+from dataclasses import dataclass
+
+from multi_swarm.ga.loop import GAConfig, next_generation
+from multi_swarm.genome.hypothesis import HypothesisAgentGenome, ModelTier
+
+_PROMPT_TEMPLATES = (
+    "Strategia mean-reversion 1h. Entry long RSI(14) < 30 e close > SMA(50). Stop 2%.",
+    "Strategia momentum breakout. Entry long close > SMA(20) e ATR(14) crescente.",
+    "Strategia trend-following 4h. Long SMA(20) > SMA(50). Short opposito.",
+)
+
+
+def _make_pop(n: int) -> list[HypothesisAgentGenome]:
+    return [
+        HypothesisAgentGenome(
+            system_prompt=_PROMPT_TEMPLATES[i % len(_PROMPT_TEMPLATES)],
+            feature_access=["close", "high"],
+            temperature=0.9 + 0.01 * i,
+            top_p=0.95,
+            model_tier=ModelTier.C,
+            lookback_window=200,
+            cognitive_style="physicist",
+        )
+        for i in range(n)
+    ]
+
+
+@dataclass
+class _Result:
+    text: str
+
+
+class _MutatorLLM:
+    """Mock che produce un prompt diverso (e valido) a ogni call."""
+
+    def __init__(self) -> None:
+        self.calls = 0
+
+    def complete(self, genome, system, user, max_tokens: int = 2000) -> _Result:
+        self.calls += 1
+        # Prompt sempre diverso per garantire validation pass.
+        return _Result(
+            text=(
+                f"<prompt>Strategia evolved #{self.calls}. Entry long quando "
+                f"RSI(14) < {25 + self.calls % 10} e close > SMA({40 + self.calls}). "
+                f"Exit short quando momentum decade. Trade rule {self.calls}.</prompt>"
+            )
+        )
+
+
+def test_loop_with_prompt_mutator_produces_prompt_diversity() -> None:
+    """Con weight 1.0 + crossover 0 (solo mutation), tutti i child non-elite
+    devono avere system_prompt diverso dai parent (LLM-mutated)."""
+    rng = random.Random(0)
+    pop = _make_pop(5)
+    fitnesses = {g.id: 0.0 for g in pop}
+    cfg = GAConfig(
+        population_size=5,
+        elite_k=1,
+        tournament_k=2,
+        p_crossover=0.0,  # nessun crossover → tutta la non-elite è mutation
+        prompt_mutation_weight=1.0,
+    )
+    llm = _MutatorLLM()
+
+    new_pop = next_generation(pop, fitnesses, cfg, rng, llm=llm)
+
+    assert len(new_pop) == 5
+    # 4 non-elite figli, tutti con prompt evoluti.
+    parent_prompts = {g.system_prompt for g in pop}
+    evolved = [g for g in new_pop[1:] if g.system_prompt not in parent_prompts]
+    assert len(evolved) >= 3, f"Solo {len(evolved)} figli con prompt mutato"
+    assert llm.calls >= 4
+
+
+def test_loop_backward_compat_no_llm_no_prompt_mutation() -> None:
+    """Default weight=0.0 + llm=None → comportamento identico a Phase 2."""
+    rng = random.Random(0)
+    pop = _make_pop(5)
+    fitnesses = {g.id: float(i) for i, g in enumerate(pop)}
+    cfg = GAConfig(
+        population_size=5,
+        elite_k=1,
+        tournament_k=2,
+        p_crossover=0.0,
+        prompt_mutation_weight=0.0,
+    )
+
+    new_pop = next_generation(pop, fitnesses, cfg, rng, llm=None)
+
+    assert len(new_pop) == 5
+    # Nessun child con prompt diverso dai parent: solo mutazioni scalari.
+    parent_prompts = {g.system_prompt for g in pop}
+    for child in new_pop:
+        assert child.system_prompt in parent_prompts

tests/unit/test_mutation_dispatcher.py

@@ -0,0 +1,102 @@
+from __future__ import annotations
+
+import random
+from collections import Counter
+from dataclasses import dataclass
+
+from multi_swarm.genome.hypothesis import HypothesisAgentGenome, ModelTier
+from multi_swarm.genome.mutation import weighted_random_mutate
+
+_PROMPT = (
+    "Strategia mean-reversion 1h BTC. Entry long quando RSI(14) < 30 e "
+    "close > SMA(50). Exit short quando RSI(14) > 70."
+)
+
+
+def _make_genome() -> HypothesisAgentGenome:
+    return HypothesisAgentGenome(
+        system_prompt=_PROMPT,
+        feature_access=["close"],
+        temperature=0.9,
+        top_p=0.95,
+        model_tier=ModelTier.C,
+        lookback_window=200,
+        cognitive_style="physicist",
+    )
+
+
+@dataclass
+class _R:
+    text: str
+
+
+class _AlwaysMutateLLM:
+    """Mock LLM che ritorna sempre un prompt mutato valido."""
+
+    def __init__(self) -> None:
+        self.calls = 0
+
+    def complete(self, genome, system, user, max_tokens: int = 2000) -> _R:
+        self.calls += 1
+        return _R(
+            text=(
+                "<prompt>Strategia momentum 1h BTC. Entry long quando close > "
+                f"SMA(70) e ATR(14) crescente. Exit con stop loss 3% (call #{self.calls}).</prompt>"
+            )
+        )
+
+
+def test_weighted_dispatcher_zero_weight_never_calls_llm() -> None:
+    llm = _AlwaysMutateLLM()
+    rng = random.Random(0)
+    parent = _make_genome()
+
+    for _ in range(50):
+        weighted_random_mutate(parent, rng, llm=llm, prompt_mutation_weight=0.0)
+
+    assert llm.calls == 0
+
+
+def test_weighted_dispatcher_full_weight_always_calls_llm() -> None:
+    llm = _AlwaysMutateLLM()
+    rng = random.Random(0)
+    parent = _make_genome()
+
+    for _ in range(20):
+        child = weighted_random_mutate(
+            parent, rng, llm=llm, prompt_mutation_weight=1.0
+        )
+        assert child.system_prompt != parent.system_prompt
+
+    assert llm.calls == 20
+
+
+def test_weighted_dispatcher_none_llm_falls_back_to_scalar() -> None:
+    """Senza llm passato (backward compat) → solo mutazione scalare."""
+    rng = random.Random(0)
+    parent = _make_genome()
+
+    for _ in range(50):
+        child = weighted_random_mutate(parent, rng, llm=None, prompt_mutation_weight=0.5)
+        assert child.system_prompt == parent.system_prompt
+
+
+def test_weighted_dispatcher_distribution_30_70() -> None:
+    """Su 1000 estrazioni con weight=0.3 il prompt mutator deve essere chiamato ~300 volte."""
+    llm = _AlwaysMutateLLM()
+    rng = random.Random(123)
+    parent = _make_genome()
+
+    counter: Counter[str] = Counter()
+    for _ in range(1000):
+        child = weighted_random_mutate(
+            parent, rng, llm=llm, prompt_mutation_weight=0.3
+        )
+        if child.system_prompt != parent.system_prompt:
+            counter["prompt"] += 1
+        else:
+            counter["scalar"] += 1
+
+    # 30% ± 5% tolerance
+    assert 250 <= counter["prompt"] <= 350, f"prompt mutations: {counter['prompt']}"
+    assert 650 <= counter["scalar"] <= 750, f"scalar mutations: {counter['scalar']}"

tests/unit/test_mutation_prompt_llm.py

@@ -0,0 +1,178 @@
+from __future__ import annotations
+
+import random
+from dataclasses import dataclass
+
+from multi_swarm.genome.hypothesis import HypothesisAgentGenome, ModelTier
+from multi_swarm.genome.mutation_prompt_llm import (
+    MUTATION_INSTRUCTIONS,
+    _extract_prompt,
+    is_valid_prompt,
+    mutate_prompt_llm,
+)
+
+_BASE_PROMPT = (
+    "Strategia mean-reversion 1h su BTC. Entry long quando RSI(14) < 30 e "
+    "close > SMA(50). Exit short quando RSI(14) > 70. Stop loss 2%."
+)
+
+
+def _make_genome(prompt: str = _BASE_PROMPT) -> HypothesisAgentGenome:
+    return HypothesisAgentGenome(
+        system_prompt=prompt,
+        feature_access=["close", "high", "low"],
+        temperature=0.9,
+        top_p=0.95,
+        model_tier=ModelTier.C,
+        lookback_window=200,
+        cognitive_style="physicist",
+    )
+
+
+@dataclass
+class _FakeResult:
+    text: str
+
+
+class _FakeLLM:
+    """Mock LLMClient: ritorna una risposta configurata in input."""
+
+    def __init__(self, response_text: str = "", raise_exc: bool = False) -> None:
+        self.response_text = response_text
+        self.raise_exc = raise_exc
+        self.last_call: dict[str, object] | None = None
+
+    def complete(
+        self,
+        genome: HypothesisAgentGenome,
+        system: str,
+        user: str,
+        max_tokens: int = 2000,
+    ) -> _FakeResult:
+        self.last_call = {
+            "genome_tier": genome.model_tier,
+            "system": system,
+            "user": user,
+            "max_tokens": max_tokens,
+        }
+        if self.raise_exc:
+            raise RuntimeError("simulated LLM failure")
+        return _FakeResult(text=self.response_text)
+
+
+def test_extract_prompt_from_tag() -> None:
+    raw = "preambolo blah\n<prompt>Strategia RSI > 75 short, SMA(60) trend.</prompt>\nblabla"
+    assert _extract_prompt(raw) == "Strategia RSI > 75 short, SMA(60) trend."
+
+
+def test_extract_prompt_no_tag_returns_stripped_text() -> None:
+    raw = "  Strategia momentum breakout su 1h con ATR(14)  "
+    assert _extract_prompt(raw) == "Strategia momentum breakout su 1h con ATR(14)"
+
+
+def test_is_valid_prompt_accepts_proper_strategy() -> None:
+    new = (
+        "Strategia mean-reversion 1h su BTC. Entry long quando RSI(14) < 25 e "
+        "close > SMA(50). Exit short quando RSI(14) > 75."
+    )
+    assert is_valid_prompt(new, _BASE_PROMPT) is True
+
+
+def test_is_valid_prompt_rejects_too_short() -> None:
+    assert is_valid_prompt("short", _BASE_PROMPT) is False
+
+
+def test_is_valid_prompt_rejects_no_strategy_keywords() -> None:
+    bad = "Questo è un testo a caso che parla del meteo di domani e della pioggia."
+    assert is_valid_prompt(bad, _BASE_PROMPT) is False
+
+
+def test_is_valid_prompt_rejects_identical_prompt() -> None:
+    assert is_valid_prompt(_BASE_PROMPT, _BASE_PROMPT) is False
+
+
+def test_mutate_prompt_llm_produces_mutated_child() -> None:
+    mutated = (
+        "Strategia mean-reversion 1h su BTC. Entry long quando RSI(14) < 25 e "
+        "close > SMA(70). Exit short quando RSI(14) > 78."
+    )
+    llm = _FakeLLM(response_text=f"<prompt>{mutated}</prompt>")
+    parent = _make_genome()
+    rng = random.Random(0)
+
+    child = mutate_prompt_llm(parent, llm, rng)
+
+    assert child.system_prompt == mutated
+    assert child.id != parent.id
+    assert child.parent_ids == [*parent.parent_ids, parent.id]
+    assert child.generation == parent.generation + 1
+    assert child.model_tier == ModelTier.C  # tier C preservato sul child
+
+
+def test_mutate_prompt_llm_uses_mutator_tier_b_for_llm_call() -> None:
+    mutated = (
+        "Strategia momentum breakout 1h. Entry long quando close > SMA(60) e "
+        "ATR(14) crescente. Exit con stop loss 3%."
+    )
+    llm = _FakeLLM(response_text=f"<prompt>{mutated}</prompt>")
+    parent = _make_genome()
+    rng = random.Random(0)
+
+    mutate_prompt_llm(parent, llm, rng)
+
+    assert llm.last_call is not None
+    assert llm.last_call["genome_tier"] == ModelTier.B
+
+
+def test_mutate_prompt_llm_falls_back_on_invalid_output() -> None:
+    """Output troppo corto -> fallback random_mutate (cambia uno scalare)."""
+    llm = _FakeLLM(response_text="<prompt>nope</prompt>")
+    parent = _make_genome()
+    rng = random.Random(42)
+
+    child = mutate_prompt_llm(parent, llm, rng)
+
+    # random_mutate preserva system_prompt, cambia uno dei 4 scalari/style.
+    assert child.system_prompt == parent.system_prompt
+    assert child.parent_ids == [*parent.parent_ids, parent.id]
+    assert child.generation == parent.generation + 1
+
+
+def test_mutate_prompt_llm_falls_back_on_identical_output() -> None:
+    llm = _FakeLLM(response_text=f"<prompt>{_BASE_PROMPT}</prompt>")
+    parent = _make_genome()
+    rng = random.Random(42)
+
+    child = mutate_prompt_llm(parent, llm, rng)
+
+    assert child.system_prompt == parent.system_prompt
+    assert child.generation == parent.generation + 1
+
+
+def test_mutate_prompt_llm_falls_back_on_llm_exception() -> None:
+    llm = _FakeLLM(raise_exc=True)
+    parent = _make_genome()
+    rng = random.Random(7)
+
+    child = mutate_prompt_llm(parent, llm, rng)
+
+    # Fallback random_mutate sempre produce un child valido.
+    assert child.system_prompt == parent.system_prompt
+    assert child.generation == parent.generation + 1
+
+
+def test_mutate_prompt_llm_picks_one_of_six_instructions() -> None:
+    """Verifica che il system message dell'LLM includa una delle 6 istruzioni."""
+    mutated = (
+        "Strategia RSI 1h. Entry long quando RSI(14) < 28 e close > SMA(50). "
+        "Exit short quando RSI(14) > 72."
+    )
+    llm = _FakeLLM(response_text=f"<prompt>{mutated}</prompt>")
+    parent = _make_genome()
+
+    mutate_prompt_llm(parent, llm, random.Random(0))
+
+    assert llm.last_call is not None
+    user_text = str(llm.last_call["user"])
+    matched_keys = [k for k in MUTATION_INSTRUCTIONS if k in user_text]
+    assert len(matched_keys) >= 1, f"User prompt non contiene istruzione: {user_text[:200]}"