feat: add complete multi-agent AI system with Telegram bot

Initial implementation of MultiAgentsAI featuring:
- Dynamic agent configuration via environment variables
- SQLite database and JSON daily context storage
- OpenRouter API integration for multiple AI models
- Telegram bot with commands for control, history, and interaction
- Autonomous conversation loop with pause/resume and agent silencing
- Model testing and statistics commands

config.py

@@ -0,0 +1,45 @@
+# Gerado por IA
+import os
+from dotenv import load_dotenv
+
+load_dotenv()
+
+
+def _parse_agents() -> list[dict]:
+    agents = []
+    idx = 1
+    while True:
+        name = os.getenv(f"AGENT_NAME_{idx}")
+        model = os.getenv(f"AGENT_MODEL_{idx}")
+        if not name or not model:
+            break
+        agents.append({"name": name, "model": model, "index": idx})
+        idx += 1
+    return agents
+
+
+class Settings:
+    # Telegram
+    TELEGRAM_BOT_TOKEN: str = os.getenv("TELEGRAM_BOT_TOKEN", "")
+    TELEGRAM_CHAT_ID: str = os.getenv("TELEGRAM_CHAT_ID", "")
+
+    # OpenRouter
+    OPENROUTER_API_KEY: str = os.getenv("OPENROUTER_API_KEY", "")
+    OPENROUTER_BASE_URL: str = os.getenv("OPENROUTER_BASE_URL", "https://openrouter.ai/api/v1")
+
+    # Sistema
+    CONVERSATION_DELAY: int = int(os.getenv("CONVERSATION_DELAY_SEGUNDOS", "30"))
+    MAX_CONTEXT_MESSAGES: int = int(os.getenv("MAX_CONTEXT_MESSAGES", "50"))
+    MAX_TOKENS: int = int(os.getenv("MAX_TOKENS", "0"))
+    DB_PATH: str = os.getenv("DB_PATH", "agents.db")
+    CONTEXTS_DIR: str = os.getenv("CONTEXTS_DIR", "Contexts")
+    CONVERSATION_LANGUAGE: str = os.getenv("CONVERSATION_LANGUAGE", "pt_BR")
+
+    # Agentes
+    AGENTS: list[dict] = _parse_agents()
+
+
+settings = Settings()
+
+# Agentes silenciados (não participam do loop automático)
+_silenced_agents: set[str] = set()