Merge remote-tracking branch 'upstream/master' into fix-user-feedback-json-error

.gitignore

@@ -12,3 +12,4 @@ outputs/*
 ai_settings.yaml
 .vscode
 auto-gpt.json
+log.txt

scripts/ai_config.py

@@ -92,4 +92,3 @@ class AIConfig:
 
         full_prompt += f"\n\n{data.load_prompt()}"
         return full_prompt
-

scripts/browse.py

@@ -15,7 +15,7 @@ def scrape_text(url):
     # Most basic check if the URL is valid:
     if not url.startswith('http'):
         return "Error: Invalid URL"
-    
+
     # Restrict access to local files
     if check_local_file_access(url):
         return "Error: Access to local files is restricted"

scripts/chat.py

@@ -63,10 +63,10 @@ def chat_with_ai(
             """
             model = cfg.fast_llm_model # TODO: Change model from hardcode to argument
             # Reserve 1000 tokens for the response
-            
+
             if cfg.debug:
                 print(f"Token limit: {token_limit}")
-                
+
             send_token_limit = token_limit - 1000
 
             relevant_memory = permanent_memory.get_relevant(str(full_message_history[-5:]), 10)

scripts/config.py

@@ -33,7 +33,7 @@ class Config(metaclass=Singleton):
 
     def __init__(self):
         """Initialize the Config class"""
-        self.debug = False
+        self.debug_mode = False
         self.continuous_mode = False
         self.speak_mode = False
 
@@ -89,9 +89,6 @@ class Config(metaclass=Singleton):
         """Set the speak mode value."""
         self.speak_mode = value
 
-    def set_debug_mode(self, value: bool):
-        self.debug_mode = value
-
     def set_fast_llm_model(self, value: str):
         """Set the fast LLM model value."""
         self.fast_llm_model = value
@@ -134,4 +131,4 @@ class Config(metaclass=Singleton):
 
     def set_debug_mode(self, value: bool):
         """Set the debug mode value."""
-        self.debug = value
+        self.debug_mode = value

scripts/file_operations.py

@@ -24,7 +24,7 @@ def read_file(filename):
     """Read a file and return the contents"""
     try:
         filepath = safe_join(working_directory, filename)
-        with open(filepath, "r") as f:
+        with open(filepath, "r", encoding='utf-8') as f:
             content = f.read()
         return content
     except Exception as e:

scripts/json_parser.py

@@ -71,11 +71,11 @@ def fix_and_parse_json(
                 return json_str
         else:
             raise e
-            
+
-        
+
 def fix_json(json_str: str, schema: str) -> str:
     """Fix the given JSON string to make it parseable and fully complient with the provided schema."""
-    
+
     # Try to fix the JSON using gpt:
     function_string = "def fix_json(json_str: str, schema:str=None) -> str:"
     args = [f"'''{json_str}'''", f"'''{schema}'''"]

scripts/json_utils.py

@@ -76,7 +76,7 @@ def balance_braces(json_string: str) -> str:
         json.loads(json_string)
         return json_string
     except json.JSONDecodeError as e:
-        raise e
+        pass
 
 
 def fix_invalid_escape(json_str: str, error_message: str) -> str:
@@ -88,7 +88,7 @@ def fix_invalid_escape(json_str: str, error_message: str) -> str:
             json.loads(json_str)
             return json_str
         except json.JSONDecodeError as e:
-            if cfg.debug:
+            if cfg.debug_mode:
                 print('json loads error - fix invalid escape', e)
             error_message = str(e)
     return json_str
@@ -103,12 +103,12 @@ def correct_json(json_str: str) -> str:
     """
 
     try:
-        if cfg.debug:
+        if cfg.debug_mode:
             print("json", json_str)
         json.loads(json_str)
         return json_str
     except json.JSONDecodeError as e:
-        if cfg.debug:
+        if cfg.debug_mode:
             print('json loads error', e)
         error_message = str(e)
         if error_message.startswith('Invalid \\escape'):
@@ -119,7 +119,7 @@ def correct_json(json_str: str) -> str:
                 json.loads(json_str)
                 return json_str
             except json.JSONDecodeError as e:
-                if cfg.debug:
+                if cfg.debug_mode:
                     print('json loads error - add quotes', e)
                 error_message = str(e)
         if balanced_str := balance_braces(json_str):

scripts/main.py

@@ -9,8 +9,6 @@ from colorama import Fore, Style
 from spinner import Spinner
 import time
 import speak
-from enum import Enum, auto
-import sys
 from config import Config
 from json_parser import fix_and_parse_json
 from ai_config import AIConfig
@@ -207,7 +205,7 @@ def load_variables(config_file="config.yaml"):
         documents = yaml.dump(config, file)
 
     prompt = data.load_prompt()
-    prompt_start = """Your decisions must always be made independently without seeking user assistance. Play to your strengths as an LLM and pursue simple strategies with no legal complications."""
+    prompt_start = """Your decisions must always be made independently without seeking user assistance. Play to your strengths as a LLM and pursue simple strategies with no legal complications."""
 
     # Construct full prompt
     full_prompt = f"You are {ai_name}, {ai_role}\n{prompt_start}\n\nGOALS:\n\n"
@@ -325,17 +323,10 @@ def parse_arguments():
         print_to_console("Speak Mode: ", Fore.GREEN, "ENABLED")
         cfg.set_speak_mode(True)
 
-    if args.debug:
-        print_to_console("Debug Mode: ", Fore.GREEN, "ENABLED")
-        cfg.set_debug_mode(True)
-
     if args.gpt3only:
         print_to_console("GPT3.5 Only Mode: ", Fore.GREEN, "ENABLED")
         cfg.set_smart_llm_model(cfg.fast_llm_model)
 
-    if args.debug:
-        print_to_console("Debug Mode: ", Fore.GREEN, "ENABLED")
-        cfg.set_debug_mode(True)
 
 
 # TODO: fill in llm values here
@@ -454,4 +445,3 @@ while True:
             chat.create_chat_message(
                 "system", "Unable to execute command"))
         print_to_console("SYSTEM: ", Fore.YELLOW, "Unable to execute command")
-

scripts/speak.py

@@ -4,6 +4,8 @@ import requests
 from config import Config
 cfg = Config()
 import gtts
+import threading
+from threading import Lock, Semaphore
 
 
 # TODO: Nicer names for these ids
@@ -14,6 +16,9 @@ tts_headers = {
     "xi-api-key": cfg.elevenlabs_api_key
 }
 
+mutex_lock = Lock() # Ensure only one sound is played at a time
+queue_semaphore = Semaphore(1) # The amount of sounds to queue before blocking the main thread
+
 def eleven_labs_speech(text, voice_index=0):
     """Speak text using elevenlabs.io's API"""
     tts_url = "https://api.elevenlabs.io/v1/text-to-speech/{voice_id}".format(
@@ -23,10 +28,11 @@ def eleven_labs_speech(text, voice_index=0):
         tts_url, headers=tts_headers, json=formatted_message)
 
     if response.status_code == 200:
-        with open("speech.mpeg", "wb") as f:
+        with mutex_lock:
-            f.write(response.content)
+            with open("speech.mpeg", "wb") as f:
-        playsound("speech.mpeg")
+                f.write(response.content)
-        os.remove("speech.mpeg")
+            playsound("speech.mpeg", True)
+            os.remove("speech.mpeg")
         return True
     else:
         print("Request failed with status code:", response.status_code)
@@ -35,21 +41,29 @@ def eleven_labs_speech(text, voice_index=0):
 
 def gtts_speech(text):
     tts = gtts.gTTS(text)
-    tts.save("speech.mp3")
+    with mutex_lock:
-    playsound("speech.mp3")
+        tts.save("speech.mp3")
-    os.remove("speech.mp3")
+        playsound("speech.mp3", True)
+        os.remove("speech.mp3")
 
 def macos_tts_speech(text):
     os.system(f'say "{text}"')
 
 def say_text(text, voice_index=0):
-    if not cfg.elevenlabs_api_key:
-        if cfg.use_mac_os_tts == 'True':
-            macos_tts_speech(text)
-        else:
-            gtts_speech(text)
-    else:
-        success = eleven_labs_speech(text, voice_index)
-        if not success:
-            gtts_speech(text)
 
+    def speak():
+        if not cfg.elevenlabs_api_key:
+            if cfg.use_mac_os_tts == 'True':
+                macos_tts_speech(text)
+            else:
+                gtts_speech(text)
+        else:
+            success = eleven_labs_speech(text, voice_index)
+            if not success:
+                gtts_speech(text)
+        
+        queue_semaphore.release()
+
+    queue_semaphore.acquire(True)
+    thread = threading.Thread(target=speak)
+    thread.start()