feat(orchestrator): end-to-end Phase 1 runner with persistence

Loop GA completo: build_initial_population -> hypothesis.propose -> falsification + adversarial -> compute_fitness -> persistenza -> next_generation. Stato run/gen/genomes/evals/cost/findings su SQLite, elite skip-eval, run marcato failed su eccezione. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-09 20:28:35 +02:00
parent 430b874b26
commit 91d160be6f
4 changed files with 261 additions and 0 deletions
@@ -0,0 +1,77 @@
+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,
+    )
+
+
+@pytest.fixture
+def fake_llm(mocker):
+    """LLM mock che ritorna sempre una strategia valida."""
+    fake = mocker.MagicMock()
+    fake.complete.return_value = CompletionResult(
+        text=(
+            "```lisp\n(strategy "
+            "(when (gt (indicator rsi 14) 70.0) (entry-short)) "
+            "(when (lt (indicator rsi 14) 30.0) (entry-long)))\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