feat(ml): add date range validation to POST /predict/batch

- Parse start_date and end_date as datetime objects
- Return HTTP 400 if end_date is before start_date
- Return HTTP 400 if date range exceeds 365 days (1 year)

Closes task 5.4 in code-review-fix tasks.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

services/ml/app/main.py

@@ -760,6 +760,28 @@ async def predict_batch(request: BatchPredictRequest):
             detail="Pipeline configuration not loaded"
         )
 
+    # Validate date range
+    try:
+        start_dt = datetime.strptime(request.start_date, "%Y-%m-%d")
+        end_dt = datetime.strptime(request.end_date, "%Y-%m-%d")
+    except ValueError as exc:
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail="Invalid date format. Use YYYY-MM-DD",
+        )
+
+    if end_dt < start_dt:
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail="end_date must be after start_date",
+        )
+
+    if (end_dt - start_dt).days > 365:
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail="Date range cannot exceed 1 year",
+        )
+
     logger.info(
         f"Batch predict: {request.pair} {request.timeframe} "
         f"from {request.start_date} to {request.end_date}"