Add multifeature direct horizon Torch forecaster

crypto_spot_bot/dashboard.py

@@ -291,9 +291,42 @@ def _time_series_model_artifact(settings: Settings) -> dict[str, Any]:
         "created_at": data.get("created_at", ""),
         "symbol_count": len(rows),
         "models": models,
+        "feature_count": _artifact_feature_count(data, rows),
+        "target_horizon": _artifact_target_horizon(data, rows),
+        "direct_horizon": _artifact_direct_horizon(data, rows),
     }
 
 
+def _artifact_feature_count(data: dict[str, Any], rows: list[Any]) -> int:
+    feature_count = data.get("feature_count")
+    if isinstance(feature_count, int):
+        return feature_count
+    counts = [
+        int(row.get("input_size", 0))
+        for row in rows
+        if isinstance(row, dict) and isinstance(row.get("input_size"), int)
+    ]
+    return max(counts) if counts else 1
+
+
+def _artifact_target_horizon(data: dict[str, Any], rows: list[Any]) -> int:
+    horizon = data.get("target_horizon")
+    if isinstance(horizon, int):
+        return horizon
+    horizons = [
+        int(row.get("target_horizon", 0))
+        for row in rows
+        if isinstance(row, dict) and isinstance(row.get("target_horizon"), int)
+    ]
+    return max(horizons) if horizons else 0
+
+
+def _artifact_direct_horizon(data: dict[str, Any], rows: list[Any]) -> bool:
+    if bool(data.get("direct_horizon")):
+        return True
+    return any(isinstance(row, dict) and bool(row.get("direct_horizon")) for row in rows)
+
+
 def _forecast_model_label(model: str, *, torch_artifact: bool = False) -> str:
     normalized = model.strip().lower()
     if normalized in {"torch_lstm", "lstm"} and torch_artifact: