feat: implement autonomous exploration mode with LLM orchestration
- Add LLMOrchestrator for LLM-first decision making - Create autonomous_mode.py as standalone entry point - Implement ExplorationSession with structured logging - Add GameContext for complete game state awareness - LLM decides strategy: explore|combat|quest|social|grinding|retreat - Automatic discovery logging (rooms, NPCs, dangers, items) - Learning memory for dangerous rooms and valuable NPCs - Session logs saved to data/autonomous_sessions/ as JSON - Real-time console output with emojis and reasoning - Fallback to rule-based when LLM unavailable - Safety overrides for low HP and high danger Usage: python -m src.autonomous_mode --duration 60 The bot now explores autonomously, learns patterns, makes strategic decisions, and saves detailed session logs for review.
This commit is contained in:
truetype committed
1 parent
43a1006223
commit
a1a0ad5840
3 files changed
+782
No files matched your search
@@ -0,0 +1,379 @@
|
||||
"""Autonomous Mode — esplorazione autonoma con LLM-first decision making.
|
||||
|
||||
Questo modulo estende il main.py per supportare una modalità completamente autonoma
|
||||
dove il bot esplora, impara e cresce da solo, orchestrato dall'LLM.
|
||||
|
||||
Usage:
|
||||
python -m src.autonomous_mode --config config.yaml --duration 60
|
||||
|
||||
La sessione viene salvata in data/autonomous_sessions/ come JSON dettagliato.
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
import argparse
|
||||
import sys
|
||||
from pathlib import Path
|
||||
from datetime import datetime, timedelta
|
||||
|
||||
sys.path.insert(0, str(Path(__file__).parent))
|
||||
|
||||
from core.telnet_client import TelnetClient
|
||||
from core.ansi_parser import ANSIParser
|
||||
from core.game_state import GameState
|
||||
from core.parsers import ParserFactory, OutputBuffer, EventType
|
||||
from config.settings import load_config
|
||||
from utils.logger import setup_logger
|
||||
from utils.human_behavior import HumanBehavior
|
||||
from modules.decision import LLMOrchestrator, GameContext
|
||||
from modules.decision.combat_ai import CombatConfig
|
||||
from modules.mapper import WorldMapper
|
||||
from modules.character import CharacterCreator, CreatorConfig
|
||||
from modules.quest import QuestManager
|
||||
from modules.progression import ProgressionOptimizer
|
||||
from modules.llm import LLMBrain, LLMConfig, SocialAI
|
||||
from modules.web import MonitoringServer
|
||||
|
||||
logger = None
|
||||
|
||||
|
||||
class AutonomousPlayer:
|
||||
"""Player autonomo che esplora e impara guidato dall'LLM."""
|
||||
|
||||
def __init__(self, config, duration_minutes: int = 60):
|
||||
self.config = config
|
||||
self.duration = timedelta(minutes=duration_minutes)
|
||||
self.orchestrator: LLMOrchestrator = None
|
||||
self.session_start: datetime = None
|
||||
self.recent_events: list = []
|
||||
self.max_events = 20
|
||||
|
||||
async def run(self):
|
||||
"""Esegue la sessione autonoma completa."""
|
||||
global logger
|
||||
|
||||
# Inizializza componenti
|
||||
telnet = TelnetClient(self.config.mud.host, self.config.mud.port)
|
||||
ansi_parser = ANSIParser()
|
||||
game_state = GameState()
|
||||
human_behavior = HumanBehavior(
|
||||
self.config.behavior.reaction_time_min_ms,
|
||||
self.config.behavior.reaction_time_max_ms,
|
||||
self.config.behavior.pause_probability,
|
||||
)
|
||||
|
||||
# Parser MUD-specifico
|
||||
mud_parser = ParserFactory.create(self.config.mud.mud_type)
|
||||
output_buffer = OutputBuffer(mud_parser)
|
||||
|
||||
# Mapper
|
||||
world_mapper = WorldMapper(
|
||||
db_path=self.config.mapper.active_storage.db_path,
|
||||
archive_dir=self.config.mapper.historical_storage.archive_dir,
|
||||
enable_sync=True,
|
||||
room_count_trigger=self.config.mapper.historical_storage.snapshot_triggers.room_count,
|
||||
time_interval_hours=self.config.mapper.historical_storage.snapshot_triggers.time_interval_hours,
|
||||
embedding_model=self.config.mapper.semantic_search.model,
|
||||
)
|
||||
|
||||
# LLM Brain (essenziale per modalità autonoma)
|
||||
llm_config = LLMConfig(
|
||||
base_url=self.config.ai.llm.base_url,
|
||||
model=self.config.ai.llm.model,
|
||||
temperature=self.config.ai.llm.temperature,
|
||||
max_tokens=self.config.ai.llm.max_tokens,
|
||||
timeout_seconds=self.config.ai.llm.timeout_seconds,
|
||||
max_retries=self.config.ai.llm.max_retries,
|
||||
system_prompt=self.config.ai.llm.system_prompt,
|
||||
)
|
||||
llm_brain = LLMBrain(llm_config, memory_db_path=self.config.ai.llm.memory_db_path)
|
||||
|
||||
if not self.config.ai.llm.enabled:
|
||||
logger.error("❌ Modalità autonoma richiede LLM abilitato!")
|
||||
return
|
||||
|
||||
await llm_brain.initialize()
|
||||
|
||||
if not llm_brain.is_available:
|
||||
logger.error("❌ LLM non disponibile. Avvia Ollama prima!")
|
||||
return
|
||||
|
||||
logger.info("🧠 LLM Brain online — Modalità autonoma pronta")
|
||||
|
||||
# Inizializza orchestratore
|
||||
self.orchestrator = LLMOrchestrator(llm_brain)
|
||||
|
||||
# Avvia sessione
|
||||
await self.orchestrator.start_session(
|
||||
character_name=self.config.character.name,
|
||||
character_class=self.config.character.preferred_class,
|
||||
initial_goals=[
|
||||
"Esplora e mappa il mondo",
|
||||
"Impara dai pattern del gioco",
|
||||
"Cresci di livello in sicurezza",
|
||||
"Interagisci socialmente con altri giocatori",
|
||||
],
|
||||
)
|
||||
|
||||
self.session_start = datetime.now()
|
||||
|
||||
# Connetti al MUD
|
||||
logger.info(f"🔌 Connessione a {self.config.mud.host}:{self.config.mud.port}")
|
||||
if not await telnet.connect():
|
||||
logger.error("❌ Connessione fallita")
|
||||
return
|
||||
|
||||
# Stato login
|
||||
login_state = "username"
|
||||
|
||||
# Callback ricezione
|
||||
async def on_receive(data: str):
|
||||
nonlocal login_state
|
||||
|
||||
clean_text = ansi_parser.strip_ansi(data)
|
||||
|
||||
# Login automatico
|
||||
if login_state == "username":
|
||||
if "login" in clean_text.lower() or "name" in clean_text.lower():
|
||||
await human_behavior.delay()
|
||||
await telnet.send(self.config.mud.username)
|
||||
login_state = "password"
|
||||
return
|
||||
elif login_state == "password":
|
||||
if "password" in clean_text.lower():
|
||||
await human_behavior.delay()
|
||||
await telnet.send(self.config.mud.password)
|
||||
login_state = "logged_in"
|
||||
return
|
||||
|
||||
if "take over" in clean_text.lower() or "copy" in clean_text.lower():
|
||||
await human_behavior.delay()
|
||||
await telnet.send("y")
|
||||
login_state = "logged_in"
|
||||
return
|
||||
|
||||
if login_state != "logged_in":
|
||||
return
|
||||
|
||||
# Processa blocchi di output
|
||||
blocks = output_buffer.feed(clean_text)
|
||||
|
||||
for block in blocks:
|
||||
events = mud_parser.parse_block(block)
|
||||
|
||||
for event in events:
|
||||
if event.event_type == EventType.PROMPT and event.prompt:
|
||||
game_state.update_from_prompt(event.prompt)
|
||||
|
||||
elif event.event_type == EventType.ROOM and event.room:
|
||||
game_state.update_room(event.room)
|
||||
|
||||
# Aggiorna mapper
|
||||
world_mapper.on_room_enter(
|
||||
title=event.room.title or "",
|
||||
description=event.room.description or "",
|
||||
exits=event.room.exits,
|
||||
npcs=event.room.npcs,
|
||||
items=event.room.items,
|
||||
)
|
||||
|
||||
# Registra scoperta
|
||||
self.orchestrator.record_discovery(
|
||||
discovery_type="room",
|
||||
description=f"{event.room.title}: {event.room.description[:100]}...",
|
||||
metadata={
|
||||
"exits": event.room.exits,
|
||||
"npcs": event.room.npcs,
|
||||
"items": event.room.items,
|
||||
}
|
||||
)
|
||||
|
||||
# Aggiungi a eventi recenti
|
||||
self._add_event(f"Entrato in: {event.room.title}")
|
||||
|
||||
elif event.event_type == EventType.COMBAT and event.combat:
|
||||
game_state.update_combat(event.combat)
|
||||
self._add_event(f"Combattimento: {event.combat.action}")
|
||||
|
||||
if event.combat.action in ["hit", "attack"]:
|
||||
self.orchestrator.record_discovery(
|
||||
discovery_type="danger",
|
||||
description=f"Combattimento in {game_state.current_room.title if game_state.current_room else 'unknown'}",
|
||||
)
|
||||
|
||||
# Social AI (sottoinsieme dell'orchestratore)
|
||||
# Per ora usiamo la logica esistente di SocialAI
|
||||
|
||||
telnet.set_receive_callback(on_receive)
|
||||
receive_task = asyncio.create_task(telnet.receive_loop())
|
||||
|
||||
try:
|
||||
logger.info("🎮 Inizio esplorazione autonoma...")
|
||||
logger.info(f"⏱️ Durata massima: {self.duration.total_seconds()/60:.0f} minuti")
|
||||
|
||||
last_decision_time = asyncio.get_running_loop().time()
|
||||
decision_interval = 3.0 # Secondi tra decisioni
|
||||
|
||||
while telnet.connected:
|
||||
# Controlla durata sessione
|
||||
elapsed = datetime.now() - self.session_start
|
||||
if elapsed > self.duration:
|
||||
logger.info("⏰ Durata massima raggiunta")
|
||||
break
|
||||
|
||||
current_time = asyncio.get_running_loop().time()
|
||||
|
||||
# Prendi decisione ogni N secondi
|
||||
if login_state == "logged_in" and (current_time - last_decision_time) >= decision_interval:
|
||||
|
||||
# Costruisci contesto
|
||||
context = self._build_game_context(game_state, world_mapper)
|
||||
|
||||
# Chiedi decisione all'LLM
|
||||
decision = await self.orchestrator.make_decision(
|
||||
context, world_mapper, game_state
|
||||
)
|
||||
|
||||
# Esegui azione
|
||||
action = decision.get("action", "look")
|
||||
|
||||
logger.info(f"🎯 Azione: {action}")
|
||||
logger.info(f" Strategia: {decision.get('strategy', 'unknown')}")
|
||||
logger.info(f" Ragionamento: {decision.get('reasoning', 'N/A')[:100]}")
|
||||
|
||||
# Notifica mapper se è un movimento
|
||||
if decision.get("strategy") == "explore" and action in ["n", "s", "e", "w", "u", "d", "north", "south", "east", "west", "up", "down"]:
|
||||
world_mapper.on_move(action)
|
||||
|
||||
await human_behavior.delay()
|
||||
await telnet.send(action)
|
||||
|
||||
last_decision_time = current_time
|
||||
|
||||
await asyncio.sleep(0.5)
|
||||
|
||||
except KeyboardInterrupt:
|
||||
logger.info("⚠️ Interrotto dall'utente")
|
||||
finally:
|
||||
# Salva sessione
|
||||
log_file = await self.orchestrator.end_session(reason="completed")
|
||||
|
||||
# Stampa riepilogo
|
||||
summary = self.orchestrator.get_session_summary()
|
||||
print(summary)
|
||||
|
||||
if log_file:
|
||||
logger.info(f"📄 Log completo: {log_file}")
|
||||
|
||||
# Cleanup
|
||||
world_mapper.close()
|
||||
await telnet.disconnect()
|
||||
receive_task.cancel()
|
||||
|
||||
def _add_event(self, event: str):
|
||||
"""Aggiunge evento alla lista recente."""
|
||||
self.recent_events.append(f"{datetime.now().strftime('%H:%M:%S')} - {event}")
|
||||
if len(self.recent_events) > self.max_events:
|
||||
self.recent_events.pop(0)
|
||||
|
||||
def _build_game_context(self, game_state: GameState, world_mapper) -> GameContext:
|
||||
"""Costruisce il contesto completo per l'LLM."""
|
||||
|
||||
# Calcola livello pericolo
|
||||
danger_level = "low"
|
||||
if game_state.current_room and game_state.current_room.npcs:
|
||||
danger_level = "medium"
|
||||
if game_state.is_in_combat():
|
||||
danger_level = "high"
|
||||
|
||||
hp_percent = game_state.character.hp / max(game_state.character.max_hp, 1)
|
||||
if hp_percent < 0.3:
|
||||
danger_level = "high"
|
||||
elif hp_percent < 0.6:
|
||||
danger_level = "medium" if danger_level == "low" else danger_level
|
||||
|
||||
return GameContext(
|
||||
current_room={
|
||||
"title": game_state.current_room.title if game_state.current_room else "Unknown",
|
||||
"description": game_state.current_room.description if game_state.current_room else "",
|
||||
"exits": list(game_state.current_room.exits.keys()) if game_state.current_room else [],
|
||||
"npcs": game_state.current_room.npcs if game_state.current_room else [],
|
||||
"items": game_state.current_room.items if game_state.current_room else [],
|
||||
},
|
||||
character_stats={
|
||||
"name": game_state.character.name,
|
||||
"class": game_state.character.class_type,
|
||||
"level": game_state.character.level,
|
||||
"hp": game_state.character.hp,
|
||||
"max_hp": game_state.character.max_hp,
|
||||
"mp": game_state.character.mp,
|
||||
"max_mp": game_state.character.max_mp,
|
||||
},
|
||||
inventory=game_state.inventory,
|
||||
recent_events=self.recent_events.copy(),
|
||||
map_stats={
|
||||
"total_rooms": world_mapper.total_rooms,
|
||||
"total_exits": world_mapper.total_exits,
|
||||
},
|
||||
exploration_queue=[], # Da implementare
|
||||
known_npcs=[],
|
||||
known_items=[],
|
||||
danger_level=danger_level,
|
||||
)
|
||||
|
||||
|
||||
def main():
|
||||
"""Entry point per modalità autonoma."""
|
||||
global logger
|
||||
|
||||
parser = argparse.ArgumentParser(description="MUD AI Player - Autonomous Mode")
|
||||
parser.add_argument("--config", default="config.yaml", help="Path to config file")
|
||||
parser.add_argument("--duration", type=int, default=60, help="Session duration in minutes")
|
||||
args = parser.parse_args()
|
||||
|
||||
# Carica configurazione
|
||||
try:
|
||||
config = load_config(args.config)
|
||||
except FileNotFoundError:
|
||||
print(f"❌ Configurazione non trovata: {args.config}")
|
||||
sys.exit(1)
|
||||
except Exception as e:
|
||||
print(f"❌ Errore caricamento config: {e}")
|
||||
sys.exit(1)
|
||||
|
||||
# Setup logging
|
||||
logger = setup_logger(
|
||||
level=config.logging.level,
|
||||
log_file=config.logging.file,
|
||||
console=config.logging.console,
|
||||
max_file_size_mb=config.logging.max_file_size_mb,
|
||||
backup_count=config.logging.backup_count,
|
||||
)
|
||||
|
||||
logger.info("=" * 60)
|
||||
logger.info("🤖 MUD AI PLAYER - AUTONOMOUS MODE")
|
||||
logger.info("=" * 60)
|
||||
logger.info(f"⏱️ Durata: {args.duration} minuti")
|
||||
logger.info(f"🧠 LLM: {config.ai.llm.model}")
|
||||
logger.info(f"🎭 Personaggio: {config.character.name} ({config.character.preferred_class})")
|
||||
logger.info("=" * 60)
|
||||
|
||||
# Verifica LLM abilitato
|
||||
if not config.ai.llm.enabled:
|
||||
logger.error("❌ Errore: LLM non abilitato in config.yaml!")
|
||||
logger.error(" Imposta ai.llm.enabled: true")
|
||||
sys.exit(1)
|
||||
|
||||
# Avvia player autonomo
|
||||
player = AutonomousPlayer(config, duration_minutes=args.duration)
|
||||
|
||||
try:
|
||||
asyncio.run(player.run())
|
||||
except Exception as e:
|
||||
logger.exception(f"❌ Errore fatale: {e}")
|
||||
sys.exit(1)
|
||||
|
||||
logger.info("✅ Sessione completata")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
Reference in new issue
Block a user