Fix circular import by moving get_data_directory to separate module

Moved get_data_directory() function from gradio_app.py to a new
data_directory.py module to avoid circular imports. The circular import
occurred because gradio_app.py imports from ui/utils.py, which was trying
to import back from gradio_app.py.

Changes:
- Create src/mosaic/data_directory.py with get_data_directory() and
set_data_directory() functions
- Update gradio_app.py to import and use set_data_directory()
- Update all other modules (aeon.py, data.py, utils.py, analysis.py) to
import from data_directory module instead of gradio_app

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

src/mosaic/analysis.py

@@ -61,7 +61,7 @@ from mussel.utils.segment import draw_slide_mask
 from mussel.cli.tessellate import BiopsySegConfig, ResectionSegConfig, TcgaSegConfig
 from loguru import logger
 from mosaic.inference import run_aeon, run_paladin
-from mosaic.gradio_app import get_data_directory
+from mosaic.data_directory import get_data_directory
 
 # Log hardware detection at module load
 logger.info(f"Hardware: {GPU_TYPE} | batch_size={DEFAULT_BATCH_SIZE}, num_workers={DEFAULT_NUM_WORKERS}")

src/mosaic/data_directory.py

@@ -0,0 +1,52 @@
+"""Data directory management for model files.
+
+This module provides a centralized function to locate the directory containing
+model data files, checking environment variables and falling back to local paths.
+"""
+
+import os
+from pathlib import Path
+
+
+# Global variable to store the model data directory path
+_MODEL_DATA_DIR = None
+
+
+def get_data_directory():
+    """Get the directory containing model data files.
+
+    Returns the HuggingFace cache directory path for the model repository,
+    or falls back to local 'data/' directory if not yet downloaded.
+
+    Returns:
+        Path: Path to the model data directory
+    """
+    global _MODEL_DATA_DIR
+    if _MODEL_DATA_DIR is not None:
+        return _MODEL_DATA_DIR
+
+    # Check if environment variable is set
+    if "MOSAIC_DATA_DIR" in os.environ:
+        _MODEL_DATA_DIR = Path(os.environ["MOSAIC_DATA_DIR"])
+        return _MODEL_DATA_DIR
+
+    # Check if local data/ directory exists (for development/backward compat)
+    local_data = Path("data")
+    if local_data.exists() and (local_data / "paladin_model_map.csv").exists():
+        _MODEL_DATA_DIR = local_data
+        return _MODEL_DATA_DIR
+
+    # Fall back to repo root data/ directory
+    _MODEL_DATA_DIR = local_data
+    return _MODEL_DATA_DIR
+
+
+def set_data_directory(path):
+    """Set the data directory path.
+
+    Args:
+        path: Path to the data directory
+    """
+    global _MODEL_DATA_DIR
+    _MODEL_DATA_DIR = Path(path)
+    os.environ["MOSAIC_DATA_DIR"] = str(_MODEL_DATA_DIR)

src/mosaic/gradio_app.py

@@ -12,8 +12,8 @@ import pandas as pd
 from pathlib import Path
 from huggingface_hub import snapshot_download
 from loguru import logger
-import os
 
+from mosaic.data_directory import set_data_directory
 from mosaic.ui import launch_gradio
 from mosaic.ui.app import set_cancer_subtype_maps
 from mosaic.ui.utils import (
@@ -26,38 +26,6 @@ from mosaic.ui.utils import (
 )
 from mosaic.analysis import analyze_slide
 
-# Global variable to store the model data directory path
-_MODEL_DATA_DIR = None
-
-
-def get_data_directory():
-    """Get the directory containing model data files.
-
-    Returns the HuggingFace cache directory path for the model repository,
-    or falls back to local 'data/' directory if not yet downloaded.
-
-    Returns:
-        Path: Path to the model data directory
-    """
-    global _MODEL_DATA_DIR
-    if _MODEL_DATA_DIR is not None:
-        return _MODEL_DATA_DIR
-
-    # Check if environment variable is set
-    if "MOSAIC_DATA_DIR" in os.environ:
-        _MODEL_DATA_DIR = Path(os.environ["MOSAIC_DATA_DIR"])
-        return _MODEL_DATA_DIR
-
-    # Check if local data/ directory exists (for development/backward compat)
-    local_data = Path("data")
-    if local_data.exists() and (local_data / "paladin_model_map.csv").exists():
-        _MODEL_DATA_DIR = local_data
-        return _MODEL_DATA_DIR
-
-    # Fall back to repo root data/ directory
-    _MODEL_DATA_DIR = local_data
-    return _MODEL_DATA_DIR
-
 
 def download_and_process_models():
     """Download models from HuggingFace and initialize cancer subtype mappings.
@@ -72,8 +40,6 @@ def download_and_process_models():
             - reversed_cancer_subtype_name_map: Dict mapping OncoTree codes to display names
             - cancer_subtypes: List of all supported cancer subtype codes
     """
-    global _MODEL_DATA_DIR
-
     # Download to HF cache directory (not local_dir)
     # This returns the path to the cached snapshot
     logger.info("Downloading models from HuggingFace Hub to cache directory...")
@@ -81,14 +47,13 @@ def download_and_process_models():
         repo_id="PDM-Group/paladin-aeon-models",
         # No local_dir - use HF cache
     )
-    _MODEL_DATA_DIR = Path(cache_dir)
-    logger.info(f"Models downloaded to: {_MODEL_DATA_DIR}")
+    logger.info(f"Models downloaded to: {cache_dir}")
 
-    # Also set environment variable for other modules to use
-    os.environ["MOSAIC_DATA_DIR"] = str(_MODEL_DATA_DIR)
+    # Set the data directory for other modules to use
+    set_data_directory(cache_dir)
 
     model_map = pd.read_csv(
-        _MODEL_DATA_DIR / "paladin_model_map.csv",
+        Path(cache_dir) / "paladin_model_map.csv",
     )
     cancer_subtypes = model_map["cancer_subtype"].unique().tolist()
     cancer_subtype_name_map = {"Unknown": "UNK"}

src/mosaic/inference/aeon.py

@@ -22,7 +22,7 @@ from mosaic.inference.data import (
 )
 
 from loguru import logger
-from mosaic.gradio_app import get_data_directory
+from mosaic.data_directory import get_data_directory
 
 # Cancer types excluded from prediction (too broad or ambiguous)
 # These are used to mask out predictions for overly general cancer types

src/mosaic/inference/data.py

@@ -13,7 +13,7 @@ import torch
 from torch.utils.data import Dataset
 import numpy as np
 
-from mosaic.gradio_app import get_data_directory
+from mosaic.data_directory import get_data_directory
 
 CANCER_TYPE_TO_INT_MAP = {
     "AASTR": 0,

src/mosaic/ui/utils.py

@@ -13,7 +13,7 @@ import pandas as pd
 import gradio as gr
 import requests
 
-from mosaic.gradio_app import get_data_directory
+from mosaic.data_directory import get_data_directory
 
 # This path should be outside your project directory if running locally
 TEMP_USER_DATA_DIR = Path(tempfile.gettempdir()) / "mosaic_user_data"