Merge remote-tracking branch 'origin/main' into codex/research-alpha158-phase3-formula-con (#10)

tests/test_alpha_factors.py

@@ -6,10 +6,14 @@ import numpy as np
 import pandas as pd
 import pytest
 
+import quant_engine.alpha_factors as alpha_factors_module
 from quant_engine.alpha_factors import (
     ALPHA158_REGISTRY,
     ALPHA158_PHASE1_OPERATOR_SPECS,
     ALPHA158_PHASE2_OPERATOR_SPECS,
+    ALPHA158_PHASE3_FORMULA_CATALOG_SHA256,
+    ALPHA158_PHASE3_FORMULA_CONTRACT_VERSION,
+    ALPHA158_PHASE3_FORMULA_SPECS,
     alpha_001,
     alpha_002,
     alpha_003,
@@ -170,8 +174,10 @@ from quant_engine.alpha_factors import (
     alpha_158,
     evaluate_phase1_operator,
     evaluate_phase2_operator,
+    evaluate_phase3_formula,
     list_phase1_operators,
     list_phase2_operators,
+    list_phase3_formulas,
     correlation,
     covariance,
     decay_linear,
@@ -1463,3 +1469,175 @@ def test_phase2_dispatch_validates_primary_series_and_unused_parameters():
         evaluate_phase2_operator("rank", values, groups=pd.Series(["x", "x", "x"]))
     with pytest.raises(ValueError, match="maximum"):
         evaluate_phase2_operator("product", values, window=253)
+
+
+# ── Alpha158 Phase 3: versioned alpha001-alpha050 formula contract ──────────
+
+
+def _phase3_market_inputs() -> dict[str, pd.Series]:
+    positions = np.arange(80, dtype=float)
+    index = pd.RangeIndex(len(positions), name="row")
+    open_ = pd.Series(100.0 + positions * 0.2 + np.sin(positions / 4.0), index=index)
+    close = pd.Series(100.5 + positions * 0.18 + np.cos(positions / 5.0), index=index)
+    high = pd.Series(np.maximum(open_, close) + 1.0, index=index)
+    low = pd.Series(np.minimum(open_, close) - 1.0, index=index)
+    volume = pd.Series(1_000.0 + positions**1.3 + 20.0 * np.sin(positions / 3.0), index=index)
+    vwap = (open_ + close + high + low) / 4.0
+    return {
+        "open": open_,
+        "close": close,
+        "high": high,
+        "low": low,
+        "volume": volume,
+        "vwap": vwap,
+    }
+
+
+def test_phase3_formula_catalog_is_versioned_exact_and_content_addressed():
+    import hashlib
+    import json
+    from collections import Counter
+
+    expected_ids = tuple(f"alpha_{number:03d}" for number in range(1, 51))
+    expected_fields = {
+        "name",
+        "contract_version",
+        "formula",
+        "category",
+        "complexity",
+        "parameters",
+        "description",
+        "references",
+        "call_inputs",
+        "formula_inputs",
+        "input_category",
+    }
+
+    assert ALPHA158_PHASE3_FORMULA_CONTRACT_VERSION == "1.0.0"
+    assert list_phase3_formulas() == expected_ids
+    assert tuple(ALPHA158_PHASE3_FORMULA_SPECS) == expected_ids
+    assert Counter(
+        spec["input_category"] for spec in ALPHA158_PHASE3_FORMULA_SPECS.values()
+    ) == {"single": 19, "pair": 26, "triple": 4, "quadruple": 1}
+
+    for alpha_id, spec in ALPHA158_PHASE3_FORMULA_SPECS.items():
+        assert set(spec) == expected_fields
+        assert spec["name"] == alpha_id
+        assert spec["contract_version"] == ALPHA158_PHASE3_FORMULA_CONTRACT_VERSION
+        assert spec["formula"] == ALPHA158_REGISTRY[alpha_id]["formula"]
+
+    serializable_specs = {
+        alpha_id: {
+            field: list(value) if isinstance(value, tuple) else value
+            for field, value in spec.items()
+        }
+        for alpha_id, spec in ALPHA158_PHASE3_FORMULA_SPECS.items()
+    }
+    encoded = json.dumps(
+        serializable_specs,
+        sort_keys=True,
+        separators=(",", ":"),
+        ensure_ascii=False,
+    ).encode()
+    assert hashlib.sha256(encoded).hexdigest() == ALPHA158_PHASE3_FORMULA_CATALOG_SHA256
+    assert ALPHA158_PHASE3_FORMULA_CATALOG_SHA256 == (
+        "9a3360e5ee77a85a35d3c2fdab1efaa531fa0c263a2cb2bb5b965a1fb96fe1bd"
+    )
+
+
+def test_phase3_formula_catalog_is_recursively_immutable():
+    import operator
+
+    with pytest.raises(TypeError):
+        operator.setitem(ALPHA158_PHASE3_FORMULA_SPECS, "alpha_001", {})
+    with pytest.raises(TypeError):
+        operator.setitem(
+            ALPHA158_PHASE3_FORMULA_SPECS["alpha_001"],
+            "formula",
+            "changed",
+        )
+    with pytest.raises(TypeError):
+        operator.setitem(
+            ALPHA158_PHASE3_FORMULA_SPECS["alpha_001"]["call_inputs"],
+            0,
+            "volume",
+        )
+
+
+def test_phase3_catalog_freezes_callable_signatures_without_rewriting_formulas():
+    import inspect
+
+    legacy_formula_input_differences = {
+        "alpha_011": ("close", "high", "low"),
+        "alpha_035": ("volume",),
+        "alpha_036": ("close",),
+        "alpha_040": ("high", "low"),
+        "alpha_042": ("close",),
+        "alpha_043": ("volume",),
+    }
+
+    for alpha_id, spec in ALPHA158_PHASE3_FORMULA_SPECS.items():
+        function = getattr(alpha_factors_module, alpha_id)
+        signature_inputs = tuple(
+            "open" if name == "open_" else name
+            for name in inspect.signature(function).parameters
+        )
+        assert spec["call_inputs"] == signature_inputs
+        assert spec["formula_inputs"] == legacy_formula_input_differences.get(
+            alpha_id,
+            signature_inputs,
+        )
+
+    assert ALPHA158_PHASE3_FORMULA_SPECS["alpha_035"]["call_inputs"] == (
+        "close",
+        "volume",
+    )
+    assert ALPHA158_REGISTRY["alpha_035"]["inputs"] == ["volume"]
+
+
+def test_phase3_dispatch_matches_all_existing_alpha001_alpha050_functions():
+    inputs = _phase3_market_inputs()
+
+    for alpha_id, spec in ALPHA158_PHASE3_FORMULA_SPECS.items():
+        call_inputs = spec["call_inputs"]
+        function = getattr(alpha_factors_module, alpha_id)
+        expected = function(*(inputs[name] for name in call_inputs))
+        actual = evaluate_phase3_formula(
+            alpha_id,
+            **{name: inputs[name] for name in reversed(call_inputs)},
+        )
+        pd.testing.assert_series_equal(actual, expected)
+
+
+def test_phase3_dispatch_rejects_unknown_missing_extra_and_non_series_inputs():
+    inputs = _phase3_market_inputs()
+
+    with pytest.raises(KeyError, match="not registered"):
+        evaluate_phase3_formula("alpha_051", close=inputs["close"])
+    with pytest.raises(ValueError, match=r"missing inputs.*volume"):
+        evaluate_phase3_formula("alpha_005", close=inputs["close"])
+    with pytest.raises(ValueError, match=r"unexpected inputs.*vwap"):
+        evaluate_phase3_formula(
+            "alpha_005",
+            close=inputs["close"],
+            volume=inputs["volume"],
+            vwap=inputs["vwap"],
+        )
+    with pytest.raises(TypeError, match="close must be a pandas Series"):
+        evaluate_phase3_formula(  # type: ignore[arg-type]
+            "alpha_005",
+            close=[1.0, 2.0],
+            volume=inputs["volume"],
+        )
+
+
+def test_phase3_dispatch_rejects_implicit_series_alignment():
+    inputs = _phase3_market_inputs()
+    misaligned_volume = inputs["volume"].rename(index={79: 80})
+
+    with pytest.raises(ValueError, match="volume index must align with close"):
+        evaluate_phase3_formula(
+            "alpha_005",
+            close=inputs["close"],
+            volume=misaligned_volume,
+        )