Add conditional Entry training probe

training/tests/test_training_contract.py

@@ -14,6 +14,7 @@ if str(TRAINING_ROOT) not in sys.path:
     sys.path.insert(0, str(TRAINING_ROOT))
 
 from trader_training.onnx_export import LinearHead, export_heads
+from trader_training.conditional_entry_probe import probe_conditional_entry_training
 from trader_training.dynamic_exit_search import search_dynamic_exit_plans
 from trader_training.entry_condition_pair_screen import screen_entry_condition_pairs
 from trader_training.entry_feature_screen import _bucket_edges, _screen_edge_column
@@ -163,6 +164,50 @@ class TrainingContractTest(unittest.TestCase):
             self.assertEqual("LONG", best["side"])
             self.assertTrue(bool(best["stable_top_edge_positive"]))
 
+    def test_conditional_entry_probe_finds_positive_oracle_direction_subset(self) -> None:
+        with tempfile.TemporaryDirectory() as tmp:
+            data_root = Path(tmp)
+            run_root = data_root / "trader-v4" / "runs" / "unit-conditional-entry"
+            dataset_path = run_root / "dataset" / "entry_train.parquet"
+            dataset_path.parent.mkdir(parents=True)
+
+            frames = []
+            row_count = 900
+            base_feature_values = np.linspace(0.0, 0.999, row_count)
+            for split_id in TRAINING_SPLITS:
+                frame = pd.DataFrame({feature: 0.0 for feature in FEATURE_ORDER}, index=np.arange(row_count))
+                frame["split_id"] = split_id
+                frame["ret_1m_bps"] = base_feature_values
+                good_mask = frame["ret_1m_bps"] > 0.85
+                opportunity_mask = frame["ret_1m_bps"] > 0.50
+                frame["long_actual_plan_net_edge_bps"] = np.where(good_mask, 10.0, -6.0)
+                frame["short_actual_plan_net_edge_bps"] = -6.0
+                frame["long_max_achievable_net_edge_bps"] = np.where(opportunity_mask, 40.0, 2.0)
+                frame["short_max_achievable_net_edge_bps"] = 2.0
+                frames.append(frame)
+            pd.concat(frames, ignore_index=True).to_parquet(dataset_path, index=False)
+
+            probe_conditional_entry_training(
+                Namespace(
+                    data_root=data_root,
+                    run_id="unit-conditional-entry",
+                    condition_opportunity_bps=(20.0,),
+                    target_edge_bps=(0.0,),
+                    model_families=("linear",),
+                    top_fractions=(0.10,),
+                    max_train_rows=0,
+                    min_train_rows=50,
+                    min_eval_rows=50,
+                )
+            )
+
+            result = read_json(run_root / "diagnostics" / "conditional_entry_probe_result.json")
+            candidates = pd.read_csv(run_root / "diagnostics" / "conditional_entry_probe_candidates.csv")
+
+            self.assertGreater(result["stable_positive_count"], 0)
+            self.assertTrue(candidates.iloc[0]["stable_positive"])
+            self.assertGreater(float(candidates.iloc[0]["min_top_edge_bps"]), 0.0)
+
     def test_dynamic_exit_search_writes_plan_diagnostics(self) -> None:
         with tempfile.TemporaryDirectory() as tmp:
             data_root = Path(tmp)