fix: AI message formatting — plain text sentences, no markdown/data dump

Schema description reinforced: brief 2-3 sentence natural language only.
Prompt template updated with example output and explicit ban on markdown
headers, bold, bullet lists, and raw field labels in the message field.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

src/ai/ai-response-schema.ts

@@ -1,7 +1,7 @@
 import { z } from 'zod';
 
 export const aiResponseSchema = z.object({
-    message: z.string().describe('Conversational response text for the agent. Plain text, no markdown.'),
+    message: z.string().describe('Brief 2-3 sentence conversational summary for the agent. Plain text only — no markdown, no headers, no bold, no bullet lists. Just natural sentences.'),
     suggestions: z.array(z.object({
         id: z.string().describe('Unique suggestion ID like s1, s2'),
         type: z.enum(['upsell', 'crosssell', 'retention', 'operational']),

src/config/ai.defaults.ts

@@ -130,7 +130,7 @@ You MUST respond with valid JSON in this exact format — no markdown fences, no
 {"message": "your response text here", "suggestions": [{"id": "s1", "type": "upsell", "title": "short title", "script": "2-3 sentence script the agent reads aloud", "priority": "high"}]}
 
 Response format rules:
-- "message" contains your conversational response to the agent. Use plain text, no markdown.
+- "message" MUST be plain text sentences only. NEVER use markdown headers (###), bold (**), bullet lists (-), or field labels (Phone:, Status:). Write natural conversational sentences like you're briefing a colleague: "Priya Sharma is a returning patient interested in IVF. She has an upcoming appointment with Dr. Patel on April 14th. Her last General Medicine appointment was rescheduled."
 - "suggestions" contains 0-4 contextual suggestions based on the SUGGESTION RULES section below (if present).
 - Each suggestion needs a personalized "script" using the caller's name, doctor, department from the context.
 - type must be one of: upsell, crosssell, retention, operational
@@ -138,6 +138,7 @@ Response format rules:
 - On the first response (patient summary), always include suggestions from the rules.
 - On subsequent responses, update suggestions based on conversation — remove acted-on ones, add new if relevant.
 - If no suggestion rules are provided, return an empty suggestions array.
+- Do NOT repeat raw data fields in the message. The summary card already shows name, phone, appointments. Keep the message to insight and context the card doesn't show.
 
 KNOWLEDGE BASE (this is real data from our system):
 {{knowledgeBase}}`;