Adriano
44eb6436c1
Sostituisce la grammatica S-expression con uno schema JSON stretto. La grammatica S-expression falliva il parsing nel 64% delle generazioni del modello Qwen3-235B sul run reale; JSON e' nativo per gli LLM moderni e si parsa con json.loads. Cambiamenti principali: - grammar.py: costanti rinominate LOGICAL_OPS / COMPARATOR_OPS / CROSSOVER_OPS / ACTION_VALUES / KIND_VALUES. - parser.py: nuovo AST a dataclass tipizzato (OpNode, IndicatorNode, FeatureNode, LiteralNode, Rule, Strategy); parse_strategy ora consuma JSON tramite json.loads. - validator.py: walk dispatchato per tipo (isinstance) invece di pattern-matching su 'kind'; arity check su operatori e indicator. - compiler.py: traversal del nuovo AST tipizzato, dispatch per isinstance; logica indicator/feature/literal invariata. - hypothesis.py: prompt SYSTEM riscritto con esempi JSON e vincoli espliciti su no-nesting; estrazione via fence ```json``` + fallback brace-balanced. - __init__.py: re-export pubblico delle entita' del protocollo. - Tutti i test (parser, validator, compiler, hypothesis_agent, falsification, adversarial, e2e, smoke_run) migrati a JSON. - Rimossa dipendenza sexpdata da pyproject.toml + uv.lock. Test: 135 passed (era 122; aggiunti casi parser/validator). ruff + mypy strict clean. Smoke run end-to-end OK. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
103 lines
2.6 KiB
Python
103 lines
2.6 KiB
Python
import json
|
|
from pathlib import Path
|
|
|
|
import numpy as np
|
|
import pandas as pd
|
|
import pytest
|
|
|
|
from multi_swarm.genome.hypothesis import ModelTier
|
|
from multi_swarm.llm.client import CompletionResult
|
|
from multi_swarm.orchestrator.run import RunConfig, run_phase1
|
|
from multi_swarm.persistence.repository import Repository
|
|
|
|
|
|
@pytest.fixture
|
|
def synthetic_ohlcv():
|
|
idx = pd.date_range("2024-01-01", periods=500, freq="1h", tz="UTC")
|
|
close = 100 + np.cumsum(np.random.RandomState(0).normal(0.01, 1.0, 500))
|
|
return pd.DataFrame(
|
|
{
|
|
"open": close,
|
|
"high": close + 0.5,
|
|
"low": close - 0.5,
|
|
"close": close,
|
|
"volume": 1.0,
|
|
},
|
|
index=idx,
|
|
)
|
|
|
|
|
|
_STRATEGY_PAYLOAD = json.dumps(
|
|
{
|
|
"rules": [
|
|
{
|
|
"condition": {
|
|
"op": "gt",
|
|
"args": [
|
|
{"kind": "indicator", "name": "rsi", "params": [14]},
|
|
{"kind": "literal", "value": 70.0},
|
|
],
|
|
},
|
|
"action": "entry-short",
|
|
},
|
|
{
|
|
"condition": {
|
|
"op": "lt",
|
|
"args": [
|
|
{"kind": "indicator", "name": "rsi", "params": [14]},
|
|
{"kind": "literal", "value": 30.0},
|
|
],
|
|
},
|
|
"action": "entry-long",
|
|
},
|
|
]
|
|
}
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def fake_llm(mocker):
|
|
"""LLM mock che ritorna sempre una strategia JSON valida."""
|
|
fake = mocker.MagicMock()
|
|
fake.complete.return_value = CompletionResult(
|
|
text="```json\n" + _STRATEGY_PAYLOAD + "\n```",
|
|
input_tokens=200,
|
|
output_tokens=80,
|
|
tier=ModelTier.C,
|
|
model="qwen",
|
|
)
|
|
return fake
|
|
|
|
|
|
def test_e2e_minimal_run_completes(
|
|
tmp_path: Path,
|
|
synthetic_ohlcv,
|
|
fake_llm,
|
|
mocker,
|
|
):
|
|
cfg = RunConfig(
|
|
run_name="e2e-test",
|
|
population_size=5,
|
|
n_generations=2,
|
|
elite_k=1,
|
|
tournament_k=2,
|
|
p_crossover=0.5,
|
|
seed=42,
|
|
model_tier=ModelTier.C,
|
|
symbol="BTC/USDT",
|
|
timeframe="1h",
|
|
fees_bp=5.0,
|
|
n_trials_dsr=10,
|
|
db_path=tmp_path / "runs.db",
|
|
)
|
|
|
|
run_id = run_phase1(cfg, ohlcv=synthetic_ohlcv, llm=fake_llm)
|
|
|
|
repo = Repository(db_path=tmp_path / "runs.db")
|
|
run = repo.get_run(run_id)
|
|
assert run["status"] == "completed"
|
|
gens = repo.list_generations(run_id)
|
|
assert len(gens) == 2
|
|
evals = repo.list_evaluations(run_id)
|
|
assert len(evals) >= 5 # almeno una popolazione
|