feat(langgraph): Usage attributes on invocation spans #5211

Bugbot Review

Bugbot Analysis Progress (3m 51s elapsed)

✅ Gathered PR context (2s)
✅ Analyzed code changes (1s)
✅ Completed bug detection — 2 potential bugs found (3m 43s)
✅ Validation and filtering completed (1s)
✅ Posted analysis results — 2 bugs reported (4s)
✅ Analysis completed successfully (0s)

Final Result: Bugbot completed review and found 2 potential issues

Request ID: serverGenReqId_fd5c2625-3c9e-4602-841c-ec2bdb263302

Bug: Usage data miscounted when PII collection disabled

When should_send_default_pii() is false or include_prompts is false, input_messages remains None. This causes _get_new_messages in _set_response_attributes to return all output messages instead of just the new ones. Since LangGraph state accumulates messages, usage data will include tokens from all messages in the response rather than only the new messages added during this invocation. The input messages need to be parsed unconditionally (at least for _get_new_messages) to correctly calculate usage data regardless of PII settings.

sentry_sdk/integrations/langgraph.py#L184-L204

sentry-python/sentry_sdk/integrations/langgraph.py

Lines 184 to 204 in 4f3fab3

    
           # Store input messages to later compare with output 
        
           input_messages = None 
        
           if ( 
        
               len(args) > 0 
        
               and should_send_default_pii() 
        
               and integration.include_prompts 
        
           ): 
        
               input_messages = _parse_langgraph_messages(args[0]) 
        
               if input_messages: 
        
                   normalized_input_messages = normalize_message_roles(input_messages) 
        
                   scope = sentry_sdk.get_current_scope() 
        
                   messages_data = truncate_and_annotate_messages( 
        
                       normalized_input_messages, span, scope 
        
                   ) 
        
                   if messages_data is not None: 
        
                       set_data_normalized( 
        
                           span, 
        
                           SPANDATA.GEN_AI_REQUEST_MESSAGES, 
        
                           messages_data, 
        
                           unpack=False, 
        
                       )

sentry_sdk/integrations/langgraph.py#L240-L260

sentry-python/sentry_sdk/integrations/langgraph.py

Lines 240 to 260 in 4f3fab3

    
           input_messages = None 
        
           if ( 
        
               len(args) > 0 
        
               and should_send_default_pii() 
        
               and integration.include_prompts 
        
           ): 
        
               input_messages = _parse_langgraph_messages(args[0]) 
        
               if input_messages: 
        
                   normalized_input_messages = normalize_message_roles(input_messages) 
        
                   scope = sentry_sdk.get_current_scope() 
        
                   messages_data = truncate_and_annotate_messages( 
        
                       normalized_input_messages, span, scope 
        
                   ) 
        
                   if messages_data is not None: 
        
                       set_data_normalized( 
        
                           span, 
        
                           SPANDATA.GEN_AI_REQUEST_MESSAGES, 
        
                           messages_data, 
        
                           unpack=False, 
        
                       )

Bug: Usage data miscounted when PII collection disabled

When should_send_default_pii() is false or include_prompts is false, input_messages remains None. This causes _get_new_messages in _set_response_attributes to return all output messages instead of just the new ones. Since LangGraph state accumulates messages, usage data will include tokens from all messages in the response rather than only the new messages added during this invocation. The input messages need to be parsed unconditionally (at least for _get_new_messages) to correctly calculate usage data regardless of PII settings.

sentry_sdk/integrations/langgraph.py#L184-L204

sentry-python/sentry_sdk/integrations/langgraph.py

Lines 184 to 204 in 4f3fab3

    
           # Store input messages to later compare with output 
        
           input_messages = None 
        
           if ( 
        
               len(args) > 0 
        
               and should_send_default_pii() 
        
               and integration.include_prompts 
        
           ): 
        
               input_messages = _parse_langgraph_messages(args[0]) 
        
               if input_messages: 
        
                   normalized_input_messages = normalize_message_roles(input_messages) 
        
                   scope = sentry_sdk.get_current_scope() 
        
                   messages_data = truncate_and_annotate_messages( 
        
                       normalized_input_messages, span, scope 
        
                   ) 
        
                   if messages_data is not None: 
        
                       set_data_normalized( 
        
                           span, 
        
                           SPANDATA.GEN_AI_REQUEST_MESSAGES, 
        
                           messages_data, 
        
                           unpack=False, 
        
                       )

sentry_sdk/integrations/langgraph.py#L240-L260

sentry-python/sentry_sdk/integrations/langgraph.py

Lines 240 to 260 in 4f3fab3

    
           input_messages = None 
        
           if ( 
        
               len(args) > 0 
        
               and should_send_default_pii() 
        
               and integration.include_prompts 
        
           ): 
        
               input_messages = _parse_langgraph_messages(args[0]) 
        
               if input_messages: 
        
                   normalized_input_messages = normalize_message_roles(input_messages) 
        
                   scope = sentry_sdk.get_current_scope() 
        
                   messages_data = truncate_and_annotate_messages( 
        
                       normalized_input_messages, span, scope 
        
                   ) 
        
                   if messages_data is not None: 
        
                       set_data_normalized( 
        
                           span, 
        
                           SPANDATA.GEN_AI_REQUEST_MESSAGES, 
        
                           messages_data, 
        
                           unpack=False, 
        
                       )

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

feat(langgraph): Usage attributes on invocation spans #5211

Uh oh!

Uh oh!

feat(langgraph): Usage attributes on invocation spans #5211

Uh oh!

Bugbot Review

Details

Bug: Usage data miscounted when PII collection disabled

Bug: Usage data miscounted when PII collection disabled

Re-running checks...

	# Store input messages to later compare with output
	input_messages = None
	if (
	len(args) > 0
	and should_send_default_pii()
	and integration.include_prompts
	):
	input_messages = _parse_langgraph_messages(args[0])
	if input_messages:
	normalized_input_messages = normalize_message_roles(input_messages)
	scope = sentry_sdk.get_current_scope()
	messages_data = truncate_and_annotate_messages(
	normalized_input_messages, span, scope
	)
	if messages_data is not None:
	set_data_normalized(
	span,
	SPANDATA.GEN_AI_REQUEST_MESSAGES,
	messages_data,
	unpack=False,
	)