refactor: Implement LLM tracing callback to improve parsing of tokens usage stats (#9311)

Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>

packages/@n8n/nodes-langchain/nodes/llms/LMOpenHuggingFaceInference/LmOpenHuggingFaceInference.node.ts

@@ -8,8 +8,8 @@ import {
 } from 'n8n-workflow';
 
 import { HuggingFaceInference } from '@langchain/community/llms/hf';
-import { logWrapper } from '../../../utils/logWrapper';
 import { getConnectionHintNoticeField } from '../../../utils/sharedFields';
+import { N8nLlmTracing } from '../N8nLlmTracing';
 
 export class LmOpenHuggingFaceInference implements INodeType {
 	description: INodeTypeDescription = {
@@ -141,10 +141,11 @@ export class LmOpenHuggingFaceInference implements INodeType {
 			model: modelName,
 			apiKey: credentials.apiKey as string,
 			...options,
+			callbacks: [new N8nLlmTracing(this)],
 		});
 
 		return {
-			response: logWrapper(model, this),
+			response: model,
 		};
 	}
 }