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>
2026-05-11 23:49:46 +02:00
parent 8ec45c5c1b
commit c38311e5fa
8 changed files with 597 additions and 4 deletions
@@ -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]}"