Adriano
c38311e5fa
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>
103 lines
2.9 KiB
Python
103 lines
2.9 KiB
Python
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']}"
|