fix: add error handling and fallback values in Parse AI Response node

- Add optional chaining (?.) for safe navigation of response properties
- Add fallback values if response fields are missing
- Extract vertrauen field directly in Parse node for easier reference
- Update Check Confidence node to reference $json.vertrauen instead of nested path
- Handles cases where LLM response format is unexpected

n8n-workflows/workflow-a-http.json

@@ -110,13 +110,18 @@
           "assignments": [
             {
               "name": "response_text",
-              "value": "={{ $json.choices[0].message.content }}",
+              "value": "={{ $json.choices?.[0]?.message?.content || '{}' }}",
               "type": "string"
             },
             {
               "name": "ai_response",
-              "value": "={{ JSON.parse($json.response_text) }}",
+              "value": "={{ typeof $json.response_text === 'string' ? JSON.parse($json.response_text) : $json.response_text }}",
               "type": "object"
+            },
+            {
+              "name": "vertrauen",
+              "value": "={{ $json.ai_response?.vertrauen || 0.5 }}",
+              "type": "number"
             }
           ]
         }
@@ -138,7 +143,7 @@
           "conditions": [
             {
               "id": "condition_1",
-              "leftValue": "={{ $json.ai_response.vertrauen }}",
+              "leftValue": "={{ $json.vertrauen }}",
               "rightValue": 0.6,
               "operator": {
                 "name": "filter.operator.gte",
@@ -183,7 +188,7 @@
             },
             {
               "name": "reason",
-              "value": "Confidence {{$json.ai_response.vertrauen}} < 0.6",
+              "value": "Confidence {{$json.vertrauen}} < 0.6",
               "type": "string"
             }
           ]