Merge remote-tracking branch 'origin/develop' into feature/add-p2-pipeline

Author: Taniya Mathur

CHANGELOG.md

@@ -11,6 +11,14 @@ SPDX-License-Identifier: MIT-0
   - Added support for Claude Haiku 4.5
   - Available for configuration across all document processing steps
 
+- **X-Ray Integration for Error Analyzer Agent**
+  - Integrated AWS X-Ray tracing tools to enhance diagnostic capabilities of the error analyzer agent
+  - X-Ray context enables better distinction between infrastructure issues and application logic failures
+  - Added trace ID persistence in DynamoDB alongside document status for complete traceability
+  - Enhanced CloudWatch error log filtering for more targeted error analysis
+  - Simplified CloudWatch results structure for improved readability and analysis
+  - Updated error analyzer recommendations to leverage X-Ray insights for more accurate root cause identification
+
 ### Changed
 
 - **Migrated UI Build System from Create React App to Vite**

config_library/pattern-1/lending-package-sample/config.yaml

@@ -242,7 +242,19 @@ agents:
       - Extract log_group, log_stream, and events data from tool response
       - Show complete log group and log stream names without truncation
       - Present actual log messages from events array in code blocks
-
+  
+      ANALYSIS GUIDELINES:
+      - If has_performance_issues is false, focus on application logic errors
+      - Use service timeline to rule out infrastructure bottlenecks
+      - Service response times help eliminate timeout-related causes
+      - For application errors use CloudWatch error messages for recommendations
+      
+      ROOT CAUSE DETERMINATION:
+      - Start with Step Function failure details (most specific)
+      - Validate with CloudWatch error logs (most detailed)
+      - Use X-Ray to categorize as infrastructure vs. application issue
+      - DynamoDB provides supporting timeline context only
+      
       RECOMMENDATION GUIDELINES:
       For code-related issues or system bugs:
       - Do not suggest code modifications

config_library/pattern-2/bank-statement-sample/config.yaml

@@ -703,7 +703,19 @@ agents:
       - Extract log_group, log_stream, and events data from tool response
       - Show complete log group and log stream names without truncation
       - Present actual log messages from events array in code blocks
-
+  
+      ANALYSIS GUIDELINES:
+      - If has_performance_issues is false, focus on application logic errors
+      - Use service timeline to rule out infrastructure bottlenecks
+      - Service response times help eliminate timeout-related causes
+      - For application errors use CloudWatch error messages for recommendations
+      
+      ROOT CAUSE DETERMINATION:
+      - Start with Step Function failure details (most specific)
+      - Validate with CloudWatch error logs (most detailed)
+      - Use X-Ray to categorize as infrastructure vs. application issue
+      - DynamoDB provides supporting timeline context only
+      
       RECOMMENDATION GUIDELINES:
       For code-related issues or system bugs:
       - Do not suggest code modifications

config_library/pattern-2/criteria-validation/config.yaml

@@ -325,7 +325,19 @@ agents:
       - Extract log_group, log_stream, and events data from tool response
       - Show complete log group and log stream names without truncation
       - Present actual log messages from events array in code blocks
-
+  
+      ANALYSIS GUIDELINES:
+      - If has_performance_issues is false, focus on application logic errors
+      - Use service timeline to rule out infrastructure bottlenecks
+      - Service response times help eliminate timeout-related causes
+      - For application errors use CloudWatch error messages for recommendations
+      
+      ROOT CAUSE DETERMINATION:
+      - Start with Step Function failure details (most specific)
+      - Validate with CloudWatch error logs (most detailed)
+      - Use X-Ray to categorize as infrastructure vs. application issue
+      - DynamoDB provides supporting timeline context only
+      
       RECOMMENDATION GUIDELINES:
       For code-related issues or system bugs:
       - Do not suggest code modifications

config_library/pattern-2/lending-package-sample/config.yaml

@@ -1482,7 +1482,19 @@ agents:
       - Extract log_group, log_stream, and events data from tool response
       - Show complete log group and log stream names without truncation
       - Present actual log messages from events array in code blocks
-
+  
+      ANALYSIS GUIDELINES:
+      - If has_performance_issues is false, focus on application logic errors
+      - Use service timeline to rule out infrastructure bottlenecks
+      - Service response times help eliminate timeout-related causes
+      - For application errors use CloudWatch error messages for recommendations
+      
+      ROOT CAUSE DETERMINATION:
+      - Start with Step Function failure details (most specific)
+      - Validate with CloudWatch error logs (most detailed)
+      - Use X-Ray to categorize as infrastructure vs. application issue
+      - DynamoDB provides supporting timeline context only
+      
       RECOMMENDATION GUIDELINES:
       For code-related issues or system bugs:
       - Do not suggest code modifications

config_library/pattern-2/rvl-cdip-package-sample-with-few-shot-examples/config.yaml

@@ -1216,7 +1216,19 @@ agents:
       - Extract log_group, log_stream, and events data from tool response
       - Show complete log group and log stream names without truncation
       - Present actual log messages from events array in code blocks
-
+  
+      ANALYSIS GUIDELINES:
+      - If has_performance_issues is false, focus on application logic errors
+      - Use service timeline to rule out infrastructure bottlenecks
+      - Service response times help eliminate timeout-related causes
+      - For application errors use CloudWatch error messages for recommendations
+      
+      ROOT CAUSE DETERMINATION:
+      - Start with Step Function failure details (most specific)
+      - Validate with CloudWatch error logs (most detailed)
+      - Use X-Ray to categorize as infrastructure vs. application issue
+      - DynamoDB provides supporting timeline context only
+      
       RECOMMENDATION GUIDELINES:
       For code-related issues or system bugs:
       - Do not suggest code modifications

config_library/pattern-2/rvl-cdip-package-sample/config.yaml

@@ -941,7 +941,19 @@ agents:
       - Extract log_group, log_stream, and events data from tool response
       - Show complete log group and log stream names without truncation
       - Present actual log messages from events array in code blocks
-
+  
+      ANALYSIS GUIDELINES:
+      - If has_performance_issues is false, focus on application logic errors
+      - Use service timeline to rule out infrastructure bottlenecks
+      - Service response times help eliminate timeout-related causes
+      - For application errors use CloudWatch error messages for recommendations
+      
+      ROOT CAUSE DETERMINATION:
+      - Start with Step Function failure details (most specific)
+      - Validate with CloudWatch error logs (most detailed)
+      - Use X-Ray to categorize as infrastructure vs. application issue
+      - DynamoDB provides supporting timeline context only
+      
       RECOMMENDATION GUIDELINES:
       For code-related issues or system bugs:
       - Do not suggest code modifications

config_library/pattern-3/rvl-cdip-package-sample/config.yaml

@@ -800,7 +800,19 @@ agents:
       - Extract log_group, log_stream, and events data from tool response
       - Show complete log group and log stream names without truncation
       - Present actual log messages from events array in code blocks
-
+  
+      ANALYSIS GUIDELINES:
+      - If has_performance_issues is false, focus on application logic errors
+      - Use service timeline to rule out infrastructure bottlenecks
+      - Service response times help eliminate timeout-related causes
+      - For application errors use CloudWatch error messages for recommendations
+      
+      ROOT CAUSE DETERMINATION:
+      - Start with Step Function failure details (most specific)
+      - Validate with CloudWatch error logs (most detailed)
+      - Use X-Ray to categorize as infrastructure vs. application issue
+      - DynamoDB provides supporting timeline context only
+      
       RECOMMENDATION GUIDELINES:
       For code-related issues or system bugs:
       - Do not suggest code modifications

lib/idp_common_pkg/idp_common/agents/common/response_utils.py

@@ -67,6 +67,12 @@ def parse_agent_response(response) -> Dict[str, Any]:
     response_str = str(response)
     logger.debug(f"Processing AgentResult as string: {response_str[:100]}...")
 
+    # Check if response looks like JSON before trying to parse
+    response_str = response_str.strip()
+    if not (response_str.startswith("{") or response_str.startswith("```")):
+        logger.debug("Response doesn't appear to be JSON, returning as text")
+        return {"responseType": "text", "content": response_str}
+
     # Extract JSON from markdown code blocks if present
     json_str = extract_json_from_markdown(response_str)
 
@@ -77,8 +83,5 @@ def parse_agent_response(response) -> Dict[str, Any]:
         )
         return parsed_response
     except json.JSONDecodeError as e:
-        logger.error(f"Failed to parse extracted JSON: {e}")
-        logger.error(f"Full LLM response: {response_str}")
-        logger.error(f"Extracted content: {json_str}")
-        # Return a text response with the raw output as fallback
+        logger.warning(f"Failed to parse as JSON, returning as text: {e}")
         return {"responseType": "text", "content": response_str}

lib/idp_common_pkg/idp_common/agents/error_analyzer/config.py

@@ -94,7 +94,7 @@ def get_context_limits() -> Dict[str, int]:
         "max_events_per_log_group": 5,
         "max_log_groups": 20,
         "max_stepfunction_timeline_events": 3,
-        "max_stepfunction_error_length": 200,
+        "max_stepfunction_error_length": 400,
         "time_range_hours_default": 24,
     }
 
@@ -143,11 +143,9 @@ def create_error_response(error: str, **kwargs) -> Dict[str, Any]:
     return response
 
 
-def create_success_response(data: Dict[str, Any]) -> Dict[str, Any]:
-    """Creates standardized success response with consistent format."""
-    response = {"success": True}
-    response.update(data)
-    return response
+def create_response(data: Dict[str, Any]) -> Dict[str, Any]:
+    """Creates standardized response with consistent format."""
+    return data
 
 
 def safe_int_conversion(value: Any, default: int = 0) -> int: