Raise coverage threshold to 95% and expand test coverage

- pyproject.toml: fail_under 80 → 95
- test_alpha: +79 lines
- test_cli_workflow: +226 lines
- test_derived: +121 lines
- test_downloader_contracts: +169 lines
- test_features: +16 lines
- test_minute_downloader: +81 lines
- test_portfolio: +208 lines

tests/test_derived.py

@@ -9,8 +9,14 @@ from click.testing import CliRunner
 
 from cli import cli
 from pipeline.alpha.compute import join_feature_frames
-from pipeline.derived.compute import compute_derived, validate_derived_frame
-from pipeline.derived.registry import available_derived, get_derived, load_derived_module
+from pipeline.derived.base import BaseDerivedData
+from pipeline.derived.compute import compute_derived, read_derived_frame, validate_derived_frame
+from pipeline.derived.registry import (
+    available_derived,
+    get_derived,
+    load_derived_module,
+    register_derived,
+)
 
 
 def _daily_bars() -> pd.DataFrame:
@@ -88,6 +94,27 @@ def test_validate_derived_frame_rejects_non_numeric_values():
         }))
 
 
+def test_validate_derived_frame_rejects_missing_value_columns():
+    with pytest.raises(ValueError, match="at least one value column"):
+        validate_derived_frame(pd.DataFrame({
+            "symbol_id": ["sh600000"],
+            "date": [pd.Timestamp("2024-01-02")],
+        }))
+
+
+def test_read_derived_frame_rejects_empty_csv(tmp_path):
+    empty_csv = tmp_path / "empty.csv"
+    empty_csv.write_text("")
+
+    with pytest.raises(ValueError, match="CSV input is empty"):
+        read_derived_frame(empty_csv)
+
+
+def test_compute_derived_rejects_missing_inputs():
+    with pytest.raises(ValueError, match="requires --daily-path or --minute-path"):
+        compute_derived("minute_daily_summary")
+
+
 def test_derived_ingest_cli_accepts_csv_and_parquet(tmp_path):
     runner = CliRunner()
     source = pd.DataFrame({
@@ -136,6 +163,26 @@ def test_derived_validate_cli_rejects_duplicate_csv_columns(tmp_path):
     assert "duplicate columns" in result.output
 
 
+def test_derived_ingest_cli_wraps_validation_errors(tmp_path):
+    runner = CliRunner()
+    csv_path = tmp_path / "bad_ingest.csv"
+    csv_path.write_text("symbol_id,date\nsh600000,2024-01-02\n")
+
+    result = runner.invoke(cli, [
+        "derived",
+        "ingest",
+        "--input-path",
+        str(csv_path),
+        "--derived-name",
+        "bad",
+        "--output-dir",
+        str(tmp_path / "derived"),
+    ])
+
+    assert result.exit_code != 0
+    assert "at least one value column" in result.output
+
+
 def test_external_derived_plugin_loads_filters_params_and_uses_inputs(tmp_path):
     module_path = tmp_path / "external_derived.py"
     module_path.write_text(textwrap.dedent('''
@@ -204,6 +251,57 @@ def test_external_derived_plugin_loads_filters_params_and_uses_inputs(tmp_path):
     assert {"daily_scaled_close", "minute_volume_sum"}.issubset(both_result.columns)
 
 
+def test_derived_registry_rejects_bad_plugins_and_load_failures(tmp_path, monkeypatch):
+    with pytest.raises(TypeError):
+        register_derived(object)  # type: ignore[arg-type]
+
+    with pytest.raises(ValueError, match="non-empty"):
+        @register_derived
+        class NoNameDerived(BaseDerivedData):
+            def compute(self, daily=None, minute=None):
+                return pd.DataFrame()
+
+    @register_derived
+    class _CoverageDerived(BaseDerivedData):
+        name = "_coverage_derived_registry"
+
+        def compute(self, daily=None, minute=None):
+            return pd.DataFrame({
+                "symbol_id": ["sh600000"],
+                "date": [pd.Timestamp("2024-01-02")],
+                "x": [1.0],
+            })
+
+    with pytest.raises(ValueError, match="already registered"):
+        @register_derived
+        class _CoverageDerivedDuplicate(BaseDerivedData):
+            name = "_coverage_derived_registry"
+
+            def compute(self, daily=None, minute=None):
+                return pd.DataFrame()
+
+    with pytest.raises(KeyError, match="Unknown derived data"):
+        get_derived("does_not_exist")
+
+    missing_path = tmp_path / "missing_derived.py"
+    with pytest.raises(FileNotFoundError):
+        load_derived_module(str(missing_path))
+
+    bad_path = tmp_path / "bad_derived.py"
+    bad_path.write_text("x = 1\n")
+    monkeypatch.setattr(
+        "pipeline.derived.registry.importlib.util.spec_from_file_location",
+        lambda *args, **kwargs: None,
+    )
+    with pytest.raises(ImportError, match="Cannot load derived data module"):
+        load_derived_module(str(bad_path))
+
+    load_derived_module("math")
+    instance = _CoverageDerived()
+    instance.scale = 2
+    assert repr(instance) == "_CoverageDerived(scale=2)"
+
+
 def test_derived_compute_cli_writes_builtin_minute_summary(tmp_path):
     runner = CliRunner()
     minute_path = tmp_path / "minute.pq"
@@ -223,6 +321,24 @@ def test_derived_compute_cli_writes_builtin_minute_summary(tmp_path):
     assert "minute_vwap" in written.columns
 
 
+def test_minute_summary_uses_time_sort_and_daily_without_close():
+    minute = _minute_bars().drop(columns=["datetime"]).sample(frac=1.0, random_state=0)
+    daily = _daily_bars()[["symbol_id", "date", "open"]]
+
+    result = compute_derived(
+        "minute_daily_summary",
+        daily=daily,
+        minute=minute,
+    )
+
+    by_symbol = result.set_index(["symbol_id", "date"])
+    assert np.isclose(
+        by_symbol.loc[("sh600000", pd.Timestamp("2024-01-02")), "minute_intraday_return"],
+        0.10,
+    )
+    assert "minute_vwap_deviation" in result.columns
+
+
 def test_alpha_feature_join_rejects_derived_column_collisions():
     data = _daily_bars()
     derived_a = data[["symbol_id", "date"]].copy()
@@ -258,4 +374,3 @@ def test_legacy_feature_cli_delegates_to_derived_registry(tmp_path):
     ])
     assert compute_result.exit_code == 0, compute_result.output
     assert (out_dir / "minute_summary.pq").exists()
-