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>
131 lines
3.8 KiB
Python
131 lines
3.8 KiB
Python
import json
|
|
|
|
from multi_swarm.agents.hypothesis import HypothesisAgent, MarketSummary
|
|
from multi_swarm.genome.hypothesis import HypothesisAgentGenome, ModelTier
|
|
from multi_swarm.llm.client import CompletionResult
|
|
|
|
|
|
def make_summary() -> MarketSummary:
|
|
return MarketSummary(
|
|
symbol="BTC/USDT",
|
|
timeframe="1h",
|
|
n_bars=1000,
|
|
return_mean=0.0001,
|
|
return_std=0.01,
|
|
skew=0.1,
|
|
kurtosis=3.5,
|
|
volatility_regime="high",
|
|
)
|
|
|
|
|
|
VALID_STRATEGY_JSON = json.dumps(
|
|
{
|
|
"rules": [
|
|
{
|
|
"condition": {
|
|
"op": "gt",
|
|
"args": [
|
|
{"kind": "indicator", "name": "rsi", "params": [14]},
|
|
{"kind": "literal", "value": 70.0},
|
|
],
|
|
},
|
|
"action": "entry-short",
|
|
}
|
|
]
|
|
}
|
|
)
|
|
|
|
|
|
def make_genome() -> HypothesisAgentGenome:
|
|
return HypothesisAgentGenome(
|
|
system_prompt="Pensa come un fisico.",
|
|
feature_access=["close"],
|
|
temperature=0.9,
|
|
top_p=0.95,
|
|
model_tier=ModelTier.C,
|
|
lookback_window=200,
|
|
cognitive_style="physicist",
|
|
)
|
|
|
|
|
|
def test_hypothesis_agent_calls_llm_and_parses(mocker): # type: ignore[no-untyped-def]
|
|
fake_llm = mocker.MagicMock()
|
|
fake_llm.complete.return_value = CompletionResult(
|
|
text=VALID_STRATEGY_JSON,
|
|
input_tokens=200,
|
|
output_tokens=80,
|
|
tier=ModelTier.C,
|
|
model="qwen",
|
|
)
|
|
agent = HypothesisAgent(llm=fake_llm)
|
|
proposal = agent.propose(make_genome(), make_summary())
|
|
assert proposal.strategy is not None
|
|
assert proposal.completion.input_tokens == 200
|
|
fake_llm.complete.assert_called_once()
|
|
|
|
|
|
def test_hypothesis_agent_returns_none_on_parse_error(mocker): # type: ignore[no-untyped-def]
|
|
fake_llm = mocker.MagicMock()
|
|
fake_llm.complete.return_value = CompletionResult(
|
|
text="this is not JSON",
|
|
input_tokens=200,
|
|
output_tokens=80,
|
|
tier=ModelTier.C,
|
|
model="qwen",
|
|
)
|
|
agent = HypothesisAgent(llm=fake_llm)
|
|
proposal = agent.propose(make_genome(), make_summary())
|
|
assert proposal.strategy is None
|
|
assert proposal.parse_error is not None
|
|
|
|
|
|
def test_hypothesis_agent_extracts_json_from_markdown_fence(mocker): # type: ignore[no-untyped-def]
|
|
fenced = (
|
|
"Ecco la strategia:\n```json\n"
|
|
+ VALID_STRATEGY_JSON
|
|
+ "\n```\nFatta."
|
|
)
|
|
fake_llm = mocker.MagicMock()
|
|
fake_llm.complete.return_value = CompletionResult(
|
|
text=fenced,
|
|
input_tokens=200,
|
|
output_tokens=80,
|
|
tier=ModelTier.C,
|
|
model="qwen",
|
|
)
|
|
agent = HypothesisAgent(llm=fake_llm)
|
|
proposal = agent.propose(make_genome(), make_summary())
|
|
assert proposal.strategy is not None
|
|
|
|
|
|
def test_hypothesis_agent_returns_error_on_invalid_strategy(mocker): # type: ignore[no-untyped-def]
|
|
bad = json.dumps(
|
|
{
|
|
"rules": [
|
|
{
|
|
"condition": {
|
|
"op": "gt",
|
|
"args": [
|
|
{"kind": "indicator", "name": "wibble", "params": [14]},
|
|
{"kind": "literal", "value": 70.0},
|
|
],
|
|
},
|
|
"action": "entry-short",
|
|
}
|
|
]
|
|
}
|
|
)
|
|
fake_llm = mocker.MagicMock()
|
|
fake_llm.complete.return_value = CompletionResult(
|
|
text=bad,
|
|
input_tokens=200,
|
|
output_tokens=80,
|
|
tier=ModelTier.C,
|
|
model="qwen",
|
|
)
|
|
agent = HypothesisAgent(llm=fake_llm)
|
|
proposal = agent.propose(make_genome(), make_summary())
|
|
assert proposal.strategy is None
|
|
assert proposal.parse_error is not None
|
|
assert "wibble" in proposal.parse_error or "unknown" in proposal.parse_error
|