fix(architect): groundedness API — remaining correction→mitigating fixes

Apply 3 additional parameter renames missed in main KB update:
- SDK: correction=True → mitigating=True
- SDK: response.corrected_text → response.correction_text
- JSON body: 'correction': false → 'mitigating': false

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

plugins/ms-ai-architect/skills/ms-ai-security/references/ai-security-engineering/output-validation-grounding-verification.md

@@ -174,7 +174,7 @@ response = client.text_detect_groundedness(
     text=llm_response,
     grounding_sources=retrieved_docs,
     reasoning=True,
-    correction=True,
+    mitigating=True,
     llm_resource={
         "resourceType": "AzureOpenAI",
         "azureOpenAIEndpoint": aoai_endpoint,
@@ -183,7 +183,7 @@ response = client.text_detect_groundedness(
 )
 
 if response.ungrounded_detected:
-    final_response = response.corrected_text
+    final_response = response.correction_text
 else:
     final_response = llm_response
 ```
@@ -352,7 +352,7 @@ Content-Type: application/json
   "text": "<LLM output>",
   "groundingSources": ["<doc1>", "<doc2>"],
   "reasoning": false,
-  "correction": false
+  "mitigating": false
 }
 ```