feat: allow markdown

enterprise/lib/captain/prompts/assistant.liquid

@@ -46,10 +46,18 @@ You can hand off conversations to these specialized scenario agents when appropr
 {% endfor %}
 
 # Response Format
-IMPORTANT: Always format your responses as valid JSON:
+CRITICAL: Always format your responses as valid JSON:
 {
   "response": "Your response to the user in clear, conversational language",
-  "reasoning": "Brief explanation of your thought process"
+  "reasoning": "Brief explanation of your actions or tool usage"
+}
+
+You can use markdown to format your response
+
+# Example
+{
+  "response": "I found the contact John Doe with email john@example.com. They have 3 open conversations.\n-CONV-32\nCONV-45",
+  "reasoning": "Used search_contact tool to locate the contact by email address"
 }
 
 # Special Cases

enterprise/lib/captain/prompts/scenario.liquid

@@ -37,8 +37,10 @@ CRITICAL: Always format your responses as valid JSON:
   "reasoning": "Brief explanation of your actions or tool usage"
 }
 
+You can use markdown to format your response
+
 # Example
 {
-  "response": "I found the contact John Doe with email john@example.com. They have 3 open conversations.",
+  "response": "I found the contact John Doe with email john@example.com. They have 3 open conversations.\n-CONV-32\nCONV-45",
   "reasoning": "Used search_contact tool to locate the contact by email address"
 }