Revise user guide and quick start instructions for clarity and accessibility in the simplified Gradio interface

src/interface/simplified_gradio_app.py

@@ -477,117 +477,110 @@ def create_simplified_interface():
             # Instructions tab
             with gr.TabItem("📖 Help", id="help"):
                 gr.Markdown("""
-## 📚 Medical Assistant with Spiritual Support
-
-### 🎯 Overview
-This is a unified medical assistant with integrated spiritual health monitoring. The system automatically detects emotional and spiritual distress while you discuss medical concerns.
-
-### 💬 Chat Tab
-**Main Interface** - Ask medical questions and receive health guidance:
-- Medical symptoms and concerns
-- Medication questions
-- Health management advice
-- Wellness support
-
-The system monitors for emotional/spiritual distress in the background and provides support when needed.
-
-### ⚙️ Model Settings Tab
-**Configure AI Models** - Choose which AI models to use for different tasks:
-- 🔍 Spiritual Monitor (Classifier) - Detects spiritual distress
-- 🟡 Soft Spiritual Triage - Asks clarifying questions
-- 📊 Triage Response Evaluator - Assesses responses
-- 🏥 Medical Assistant - Provides medical guidance
-- 🩺 Soft Medical Triage - Gentle health check-ins
-
-**Available Models:**
-- Claude (Anthropic) - Best for empathy and nuanced understanding
-- Gemini (Google) - Fast and efficient for classification
-
-### 👥 Patient Profiles Tab
-**Test Different Scenarios** - Load predefined patient profiles:
-
-**Testing Spiritual Functionality:**
-- 🟢 GREEN - Healthy: No distress indicators
-- 🟡 YELLOW - Mild Distress: Stress, anxiety, sleep issues
-- 🟡 YELLOW - Grief & Loss: Processing loss
-- 🟡 YELLOW - Existential Questions: Life meaning concerns
-- 🟡 YELLOW - Spiritual Disconnection: Loss of faith
-- 🔴 RED - Crisis (Suicidal): Immediate intervention needed
-- 🔴 RED - Severe Hopelessness: Complete despair
-- 🔴 RED - Spiritual Crisis: Moral injury, anger at God
-
-**Medical Profiles:**
-- Cardiac Patient, Diabetic Patient, Post-Surgery Recovery
-- Mental Health Focus, Elderly Patient, Athletic Patient
-
-### 🔧 Edit Prompts Tab
-**Customize System Prompts** - Modify AI behavior for your session:
-- 🔍 Spiritual Monitor (Classifier)
-- 🟡 Soft Spiritual Triage
-- 📊 Triage Response Evaluator
-- 🏥 Medical Assistant
-- 🩺 Soft Medical Triage
-
-Changes apply only to your current session.
-
-### 🟢 GREEN State
-**No Distress Detected** - Normal medical conversation
-- Medical symptoms only
-- Routine health questions
-- Standard healthcare topics
-
-### 🟡 YELLOW State
-**Potential Distress Detected** - Gentle triage begins
-- Emotional or spiritual concerns detected
-- System asks 2-3 clarifying questions
-- Assesses if patient needs referral
-
-**Indicators:**
-- Stress, anxiety, worry
-- Grief or loss
-- Existential questions
-- Loneliness or isolation
-- Feeling overwhelmed
-
-### 🔴 RED State
-**Severe Distress - Immediate Referral**
-- Crisis language detected
-- Suicidal ideation
-- Severe hopelessness
-- Spiritual crisis
-
-**Immediate Actions:**
-- Referral generated
-- Spiritual care team notified
-- Crisis resources provided
-
-### 💭 Spiritual Distress Examples
-
-**YELLOW Indicators:**
-- "I'm feeling stressed and overwhelmed"
-- "I've lost my faith lately"
-- "I feel so alone since my spouse passed"
-- "What's the point of all this suffering?"
-- "I can't sleep, I'm so anxious"
-
-**RED Indicators:**
-- "I want to end it all"
-- "I can't go on anymore"
-- "I'm so angry at God"
-- "Nobody would miss me"
-- "I have no reason to live"
-
-### ⚠️ Important
-- This is NOT a replacement for professional medical care
-- For emergencies, call emergency services immediately
-- Crisis support is available 24/7
-- All conversations are confidential
-
-### 🔐 Privacy & Security
-- Session data is stored locally
-- No data is shared externally
-- Each session is independent
-- Clear chat to remove history
+## 📖 User Guide (Non‑Technical)
+
+### What this app is
+This is a **Medical Assistant** that also watches for **emotional / spiritual distress** in the background.
+You can chat naturally about health and lifestyle. If the system detects distress, it gently adapts the conversation.
+
+---
+
+## 🚀 Quick Start
+
+### Quick Start: Chat (everyday use)
+1. Open the **Chat** tab.
+2. Type your question (symptoms, medications, lifestyle, recovery, etc.).
+3. Read the response.
+4. If the system detects distress, it may ask a few gentle follow‑up questions.
+
+### Quick Start: Testing / QA (Enhanced Verification)
+1. Open **Enhanced Verification**.
+2. Choose one mode:
+    - **Manual Input** (test one message)
+    - **File Upload** (test many messages in a batch)
+3. Run classification.
+4. Export results as **CSV** or **JSON**.
+
+---
+
+## 💬 Chat: What to expect
+Use Chat for:
+- health questions and symptoms
+- medication questions
+- recovery and rehab guidance
+- lifestyle support (activity, nutrition, habits)
+
+The system continuously monitors messages for possible distress while you chat.
+
+---
+
+## 🧭 Distress levels (how the system reacts)
+You may see one of these behaviors during a conversation:
+
+### 🟢 GREEN — No distress detected
+Normal medical conversation.
+
+### 🟡 YELLOW — Possible distress
+The assistant may ask **2–3 short, gentle questions** to clarify what you’re going through.
+Goal: understand whether extra support (like a referral) may be helpful.
+
+### 🔴 RED — Severe distress / safety concern
+The assistant prioritizes safety and guidance.
+It may generate referral‑style guidance and suggest urgent help.
+
+---
+
+## ⚙️ Model Settings (AI Model Configuration)
+You can choose which AI model is used for different tasks (e.g., monitoring vs. medical advice).
+
+**Session‑only:** Model changes apply only to your **current session**.
+Starting a new session resets to defaults.
+
+---
+
+## 🔧 Edit Prompts (Customize behavior)
+Prompts control *how* the AI behaves (tone, structure, rules).
+
+**Session‑only:** Prompt edits apply only to your **current session**.
+They do not affect other sessions.
+
+Tip: after you click **Apply Changes**, the next message or batch run will use the updated prompt.
+
+---
+
+## ✅ Enhanced Verification (Testing modes)
+Enhanced Verification is a testing/validation environment. It helps you measure quality and export results.
+
+### ✏️ Manual Input Mode
+Use this when you want to test a single message quickly:
+1. Enter a message.
+2. Run classification.
+3. Review results and save the verification.
+
+### 📁 File Upload Mode
+Use this when you want to test an entire dataset:
+1. Download the CSV template (in the UI).
+2. Fill in your test messages.
+3. Upload the CSV.
+4. Start **batch classification** (one click).
+5. Review totals and accuracy.
+
+---
+
+## 💾 Exports
+Exports are available in Enhanced Verification:
+- **CSV**
+- **JSON**
+
+CSV note:
+- The **Notes** column contains **only the model `reasoning`** (when present).
+
+---
+
+## 🔐 Privacy & Safety
+- Session data is stored locally.
+- This tool does not replace professional medical advice.
+- If there is an emergency, contact local emergency services.
                 """)
         
         # Event handlers