refactor: update logging configuration for reduced verbosity and improved outlier handling

app.py

@@ -19,9 +19,9 @@ from typing import List, Dict, Any
 # from app_trans_new import create_transcation_visualizations,create_active_agents_visualizations
 # APR visualization functions integrated directly
 
-# Set up more detailed logging
+# Set up logging with appropriate verbosity
 logging.basicConfig(
-    level=logging.DEBUG,  # Change to DEBUG for more detailed logs
+    level=logging.INFO,  # Use INFO level instead of DEBUG to reduce verbosity
     format="%(asctime)s - %(levelname)s - %(message)s",
     handlers=[
         logging.FileHandler("app_debug.log"),  # Log to file for persistence
@@ -30,6 +30,11 @@ logging.basicConfig(
 )
 logger = logging.getLogger(__name__)
 
+# Reduce third-party library logging
+logging.getLogger("urllib3").setLevel(logging.WARNING)
+logging.getLogger("httpx").setLevel(logging.WARNING)
+logging.getLogger("matplotlib").setLevel(logging.WARNING)
+
 # Log the startup information
 logger.info("============= APPLICATION STARTING =============")
 logger.info(f"Running from directory: {os.getcwd()}")
@@ -471,63 +476,10 @@ def create_time_series_graph_per_agent(df):
     return fig
 
 def write_debug_info(df, fig):
-    """Write detailed debug information to logs for troubleshooting"""
+    """Minimal debug info function"""
     try:
-        logger.info("==== GRAPH DEBUG INFORMATION ====")
-        logger.info(f"Total data points: {len(df)}")
-        logger.info(f"DataFrame columns: {df.columns.tolist()}")
-        
-        logger.info("Data types:")
-        for col in df.columns:
-            logger.info(f"  {col}: {df[col].dtype}")
-        
-        # Output sample data points
-        logger.info("Sample data (up to 5 rows):")
-        sample_df = df.head(5)
-        for idx, row in sample_df.iterrows():
-            logger.info(f"  Row {idx}: {row.to_dict()}")
-        
-        # Output Plotly figure structure
-        logger.info("Plotly Figure Structure:")
-        logger.info(f"  Number of traces: {len(fig.data)}")
-        for i, trace in enumerate(fig.data):
-            logger.info(f"  Trace {i}:")
-            logger.info(f"    Type: {trace.type}")
-            logger.info(f"    Mode: {trace.mode if hasattr(trace, 'mode') else 'N/A'}")
-            logger.info(f"    Name: {trace.name}")
-            
-            # Only log first few values to avoid overwhelming logs
-            if hasattr(trace, 'x') and trace.x is not None and len(trace.x) > 0:
-                x_sample = str(trace.x[:2])
-                logger.info(f"    X data sample (first 2): {x_sample}")
-            
-            if hasattr(trace, 'y') and trace.y is not None and len(trace.y) > 0:
-                y_sample = str(trace.y[:2])
-                logger.info(f"    Y data sample (first 2): {y_sample}")
-            
-            if hasattr(trace, 'line') and hasattr(trace.line, 'color'):
-                logger.info(f"    Line color: {trace.line.color}")
-            
-            if hasattr(trace, 'line') and hasattr(trace.line, 'width'):
-                logger.info(f"    Line width: {trace.line.width}")
-        
-        # Check environment
-        import os
-        import sys
-        import platform
-        
-        logger.info("Environment Information:")
-        logger.info(f"  Platform: {platform.platform()}")
-        logger.info(f"  Python version: {sys.version}")
-        logger.info(f"  Running in Docker: {'DOCKER_CONTAINER' in os.environ}")
-        logger.info(f"  Running in HF Space: {'SPACE_ID' in os.environ}")
-        
-        # Plotly version
-        import plotly
-        logger.info(f"  Plotly version: {plotly.__version__}")
-        
-        logger.info("End of debug info")
-        
+        # Just log minimal information
+        logger.debug(f"Graph created with {len(df)} data points and {len(fig.data)} traces")
         return True
     except Exception as e:
         logger.error(f"Error writing debug info: {e}")
@@ -629,17 +581,24 @@ def create_combined_time_series_graph(df):
     )
     
     # MODIFIED: Calculate average APR values across all agents for each timestamp
-    # Filter for APR data only and exclude the problematic agent
+    # Filter for APR data only
     apr_data = df[df['metric_type'] == 'APR'].copy()
     
-    # Filter out the agent with abnormally high APR values
-    agent_to_exclude = "rimyi-kilus56"
-    apr_data_filtered = apr_data[apr_data['agent_name'] != agent_to_exclude].copy()
+    # Filter out outliers (APR values above 200 or below -200)
+    outlier_data = apr_data[(apr_data['apr'] > 200) | (apr_data['apr'] < -200)].copy()
+    apr_data_filtered = apr_data[(apr_data['apr'] <= 200) & (apr_data['apr'] >= -200)].copy()
     
-    # Log the filtering
-    if len(apr_data) != len(apr_data_filtered):
-        excluded_count = len(apr_data) - len(apr_data_filtered)
-        logger.info(f"Excluded {excluded_count} data points from agent '{agent_to_exclude}' due to abnormally high APR values")
+    # Log the outliers for better debugging
+    if len(outlier_data) > 0:
+        excluded_count = len(outlier_data)
+        logger.info(f"Excluded {excluded_count} data points with outlier APR values (>200 or <-200)")
+        
+        # Group outliers by agent for detailed logging
+        outlier_agents = outlier_data.groupby('agent_name')
+        for agent_name, agent_outliers in outlier_agents:
+            logger.info(f"Agent '{agent_name}' has {len(agent_outliers)} outlier values:")
+            for idx, row in agent_outliers.iterrows():
+                logger.info(f"  - APR: {row['apr']}, timestamp: {row['timestamp']}")
     
     # Use the filtered data for all subsequent operations
     apr_data = apr_data_filtered
@@ -806,7 +765,7 @@ def create_combined_time_series_graph(df):
     # Update layout - use simple boolean values everywhere
     # Increase the width and height for better visualization
     fig.update_layout(
-        title="Average APR Values Across All Agents",
+        title="Babydegen agents",
         xaxis_title="Time",
         yaxis_title="Value",
         template="plotly_white",
@@ -1001,7 +960,7 @@ def create_combined_time_series_graph(df):
         
         # Simplified layout with adjusted y-axis range and increased size
         simple_fig.update_layout(
-            title="Average APR Values Across All Agents",
+            title="Babydegen agents",
             xaxis_title="Time",
             yaxis_title="Value",
                     yaxis=dict(