update stop phrases, exit and quit only, calibrated how sensitive the mood detection is

Author: bigsk1

.env.sample

@@ -87,4 +87,5 @@ DEBUG=false
 # List of trigger phrases to have the model view your desktop (desktop, browser, images, etc.).
 # It will describe what it sees, and you can ask questions about it:
 # "what's on my screen", "take a screenshot", "show me my screen", "analyze my screen", 
-# "what do you see on my screen", "screen capture", "screenshot"
+# "what do you see on my screen", "screen capture", "screenshot"
+# To stop the conversation, say "Quit" or "Exit". ( ctl+c always works also)

README.md

@@ -413,7 +413,7 @@ DEBUG=false
 # It will describe what it sees, and you can ask questions about it:
 # "what's on my screen", "take a screenshot", "show me my screen", "analyze my screen", 
 # "what do you see on my screen", "screen capture", "screenshot"
-# To stop the conversation, say "Quit", "Exit", or "Leave". ( ctl+c always works also)
+# To stop the conversation, say "Quit" or "Exit". ( ctl+c always works also)
 ```
 
 ### Audio Commands
@@ -426,7 +426,7 @@ DEBUG=false
         "what do you see on my screen",
         "screen capture",
         "screenshot" to have the AI explain what it is seeing in detail.
-- To stop the conversation, say "Quit", "Exit", or "Leave". ( ctl+c always works also in terminal )
+- To stop the conversation, say "Quit" or "Exit". ( ctl+c always works also in terminal )
 
 ### ElevenLabs
 
@@ -489,7 +489,7 @@ For the CLI version, the voice ID in the .env file will be used.
 
 ### Web View - Visual and Audio input / output
 
-Press start to start talking. Take a break hit stop, when ready again hit start again. Press stop to change characters and voices in dropdown. You can also select the Model Provider and TTS Provider you want in the dropdown menu and it will update and use the selected provider moving forward. Saying Exit, Leave or Quit is like pressing stop.
+Press start to start talking. Take a break hit stop, when ready again hit start again. Press stop to change characters and voices in dropdown. You can also select the Model Provider and TTS Provider you want in the dropdown menu and it will update and use the selected provider moving forward. Saying Exit or Quit is like pressing stop.
 
 http://localhost:8000/
 
@@ -711,7 +711,7 @@ Model provider: openai
 Model: gpt-4o
 Character: Nerd
 Text-to-Speech provider: elevenlabs
-To stop chatting say Quit, Leave or Exit. Say, what's on my screen, to have AI view screen. One moment please loading...
+To stop chatting say Quit or Exit. Say, what's on my screen, to have AI view screen. One moment please loading...
 INFO:     Started server process [12752]
 INFO:     Waiting for application startup.
 INFO:     Application startup complete.

app/app.py

@@ -239,7 +239,7 @@ def sync_play_audio(file_path):
 print(f"Model: {OPENAI_MODEL if MODEL_PROVIDER == 'openai' else XAI_MODEL if MODEL_PROVIDER == 'xai' else OLLAMA_MODEL}")
 print(f"Character: {character_display_name}")
 print(f"Text-to-Speech provider: {TTS_PROVIDER}")
-print("To stop chatting say Quit, Leave or Exit. Say, what's on my screen, to have AI view screen. One moment please loading...")
+print("To stop chatting say Quit or Exit. One moment please loading...")
 
 async def process_and_play(prompt, audio_file_pth):
     # Always get the current character name to ensure we have the right audio file
@@ -517,7 +517,7 @@ def analyze_mood(user_input):
         "yucky", "ugh", "eww", "blegh", "blech", "ew"
     ]
     happy_keywords = [
-        "happy", "pleased", "content", "satisfied", "good", "great",
+        "happy", "pleased", "content", "satisfied", "great",
         "positive", "upbeat", "bright", "cheery", "merry", "lighthearted",
         "gratified", "blessed", "fortunate", "lucky", "peaceful", "serene", 
         "comfortable", "at ease", "fulfilled", "optimistic", "hopeful", "sunny",
@@ -547,24 +547,24 @@ def analyze_mood(user_input):
     ]
 
     mood = "neutral"  # Default value
-    
+
     if any(keyword in user_input.lower() for keyword in flirty_keywords):
         mood = "flirty"
-    elif any(keyword in user_input.lower() for keyword in angry_keywords):
+    elif any(keyword in user_input.lower() for keyword in angry_keywords) or polarity < -0.7:
         mood = "angry"
-    elif any(keyword in user_input.lower() for keyword in sad_keywords):
+    elif any(keyword in user_input.lower() for keyword in sad_keywords) or polarity < -0.3:
         mood = "sad"
     elif any(keyword in user_input.lower() for keyword in fearful_keywords):
         mood = "fearful"
     elif any(keyword in user_input.lower() for keyword in surprised_keywords):
         mood = "surprised"
     elif any(keyword in user_input.lower() for keyword in disgusted_keywords):
         mood = "disgusted"
-    elif any(keyword in user_input.lower() for keyword in happy_keywords):
+    elif any(keyword in user_input.lower() for keyword in happy_keywords) or polarity > 0.7:
         mood = "happy"
-    elif any(keyword in user_input.lower() for keyword in joyful_keywords) or polarity > 0.3:
+    elif any(keyword in user_input.lower() for keyword in joyful_keywords) or polarity > 0.4:
         mood = "joyful"
-    elif any(keyword in user_input.lower() for keyword in neutral_keywords):
+    elif any(keyword in user_input.lower() for keyword in neutral_keywords) or (-0.3 <= polarity <= 0.4):
         mood = "neutral"
 
     # Color mapping for different moods
@@ -585,6 +585,7 @@ def analyze_mood(user_input):
 
     # Print the detected mood with the corresponding color
     print(f"{color}Detected mood: {mood}\033[0m")
+    print()  # Add an empty line for spacing in CLI output
 
     return mood
 
@@ -1075,7 +1076,7 @@ async def user_chatbot_conversation():
 
     base_system_message = open_file(character_prompt_file)
 
-    quit_phrases = ["quit", "Quit", "Quit.", "Exit.", "exit", "Exit", "leave", "Leave."]
+    quit_phrases = ["quit", "Quit", "Quit.", "Exit.", "exit", "Exit"]
     screenshot_phrases = [
         "what's on my screen", 
         "take a screenshot", 
@@ -1096,7 +1097,7 @@ async def user_chatbot_conversation():
 
             # Check for quit phrases with word boundary check
             words = user_input.lower().split()
-            if any(phrase.lower().rstrip('.') in words for phrase in quit_phrases):
+            if any(phrase.lower().rstrip('.') == word for phrase in quit_phrases for word in words):
                 print("Quitting the conversation...")
                 break
 

app/app_logic.py

@@ -116,7 +116,7 @@ async def process_text(user_input):
 
     return chatbot_response
 
-quit_phrases = ["quit", "Quit", "Quit.", "Exit.", "exit", "Exit", "leave", "Leave."]
+quit_phrases = ["quit", "Quit", "Quit.", "Exit.", "exit", "Exit"]
 screenshot_phrases = [
     "what's on my screen", 
     "take a screenshot", 
@@ -252,7 +252,7 @@ async def conversation_loop():
 
         # Check for quit phrases with word boundary check
         words = user_input.lower().split()
-        if any(phrase.lower() in words for phrase in quit_phrases):
+        if any(phrase.lower().rstrip('.') == word for phrase in quit_phrases for word in words):
             print("Quitting the conversation...")
             await stop_conversation()
             break

app/enhanced_logic.py

@@ -31,7 +31,7 @@
 DEBUG = os.getenv("DEBUG", "false").lower() == "true"  # Control detailed debug output
 
 # Quit phrases that will stop the conversation when detected
-QUIT_PHRASES = ["quit", "exit", "leave", "end", "bye", "goodbye"]
+QUIT_PHRASES = ["quit", "exit"]
 
 def load_character_prompt(character_name):
     """
@@ -556,7 +556,8 @@ async def save_history():
                 await send_message_to_enhanced_clients({"action": "mic", "status": "processing"})
 
                 # Check for quit commands
-                if user_input.lower() in QUIT_PHRASES:
+                words = user_input.lower().split()
+                if any(phrase.lower().rstrip('.') == word for phrase in QUIT_PHRASES for word in words):
                     await send_message_to_enhanced_clients({"message": "Conversation ended.", "type": "system-message"})
                     break
 

app/templates/enhanced.html

@@ -270,8 +270,8 @@ <h1>
                     <option value="sage">Sage - female</option>
                     <option value="coral">Coral - female</option>
                     <option value="ash">Ash - male</option>
-                    <option value="ballad">Ballad - male</option>
-                    <option value="verse">Verse - male</option>
+                    <option value="ballad">Ballad - male - no tts-1</option>
+                    <option value="verse">Verse - male - no tts-1</option>
                 </select>
             </div>
 

characters/caffeinated_psychic/caffeninated_psychic.wav renamed to characters/caffeinated_psychic/caffeinated_psychic.wav

@@ -168,7 +168,7 @@ def play_audio(file_path):
 print(f"Character: {character_display_name}")
 print(f"Text-to-Speech provider: {TTS_PROVIDER}")
 print(f"Text-to-Speech model: {OPENAI_MODEL_TTS if TTS_PROVIDER == 'openai' else ELEVENLABS_TTS_MODEL if TTS_PROVIDER == 'elevenlabs' else 'local' if TTS_PROVIDER == 'xtts' else 'Unknown'}")
-print("To stop chatting say Quit, Leave or Exit. Say, what's on my screen, to have AI view screen. One moment please loading...")
+print("To stop chatting say Quit or Exit. One moment please loading...")
 
 # Function to synthesize speech using XTTS
 def process_and_play(prompt, audio_file_pth):
@@ -1076,7 +1076,7 @@ def user_chatbot_conversation():
             conversation_history = []
 
     base_system_message = open_file(character_prompt_file)
-    quit_phrases = ["quit", "Quit", "Quit.", "Exit.", "exit", "Exit", "leave", "Leave", "Leave."]
+    quit_phrases = ["quit", "Quit", "Quit.", "Exit.", "exit", "Exit"]
     screenshot_phrases = [
         "what's on my screen", 
         "take a screenshot",