# Recuperación de errores para agentes Los errores ocurren. Las redes fallan, las APIs devuelven 500s, los Mind Keys expiran. Esta guía muestra cómo los agentes LLM deben manejar errores de forma elegante y aprender de ellos. ## Principios de manejo de errores 1. **Reintente con backoff** — los errores transitorios suelen resolverse 2. **Almacene el error** — aprenda de los patrones 3. **Degrade de forma elegante** — no bloquee toda la sesión 4. **Notifique al humano** — para errores que no pueda resolver ## Manejo de errores HTTP ### Reintento con backoff exponencial ```python import time import requests def call_with_retry(url, max_retries=3, backoff_base=2): """Call URL with exponential backoff.""" for attempt in range(max_retries): try: r = requests.get(url, headers={"Authorization": f"Bearer {KEY}"}) # Success if r.status_code < 400: return r # Rate limited — wait and retry if r.status_code == 429: wait = int(r.headers.get("Retry-After", 60)) print(f"Rate limited. Waiting {wait}s...") time.sleep(wait) continue # Server error — retry with backoff if r.status_code >= 500: wait = backoff_base ** attempt print(f"Server error {r.status_code}. Retrying in {wait}s...") time.sleep(wait) continue # Client error — don't retry if 400 <= r.status_code < 500: raise ClientError(f"{r.status_code}: {r.text}") except requests.RequestException as e: # Network error — retry wait = backoff_base ** attempt print(f"Network error: {e}. Retrying in {wait}s...") time.sleep(wait) raise MaxRetriesError(f"Failed after {max_retries} retries") ``` ### Manejo de errores de auth ```python def safe_call(url): """Call with auth error handling.""" try: return call_with_retry(url) except ClientError as e: if "401" in str(e): # Mind Key invalid — critical, can't recover store_error("auth_invalid", str(e), "Check Mind Key") notify_human("My Mind Key is invalid. Please update.") raise AuthError("Cannot continue without valid Mind Key") elif "403" in str(e): store_error("forbidden", str(e), "Wrong token type?") raise ForbiddenError(str(e)) elif "404" in str(e): # Path doesn't exist — don't retry store_error("not_found", str(e), "Check endpoint path") raise NotFoundError(str(e)) else: raise ``` ## Almacenar errores como memorias Cuando ocurren errores, almacénelos para que las sesiones futuras puedan aprender: ```python def store_error(error_type, error_message, recovery_hint=""): """Store an error as a memory for future reference.""" requests.post(f"{URL}/memory", headers={"Authorization": f"Bearer {KEY}", "Content-Type": "application/json"}, json={ "category": "mistake", "key": f"error_{error_type}_{int(time.time())}", "content": f"Error: {error_type}\nMessage: {error_message}\nRecovery: {recovery_hint}", "tags": ["error", error_type], "priority": "high" }) # Example try: deploy() except DeployError as e: store_error("deploy_failed", str(e), "Check CI logs, verify Docker image exists") raise ``` ## Escenarios de error comunes ### Escenario 1: Mind Key inválido ```python # Detection: 401 on every call # Recovery: Cannot recover — need human intervention def handle_invalid_mind_key(): store_error("mind_key_invalid", "All API calls returning 401", "Mind Key may be revoked. Need new key.") # Notify human via chat (if possible) try: reply("⚠️ My Mind Key is invalid. I cannot access memories. " "Please check and update SYNAPSE_MIND_KEY.") except: pass # Chat may also fail with bad key # Exit gracefully raise CriticalError("Cannot continue without valid Mind Key") ``` ### Escenario 2: Error de red ```python # Detection: ConnectionError, Timeout # Recovery: Retry with backoff, then degrade def handle_network_error(url, retry=3): for attempt in range(retry): try: return requests.get(url, timeout=10) except (requests.ConnectionError, requests.Timeout) as e: wait = 2 ** attempt print(f"Network error, retrying in {wait}s: {e}") time.sleep(wait) # All retries failed — degrade store_error("network_failure", f"Cannot reach {url}", "Check internet connection, Synapse may be down") # Work offline if possible return work_offline() ``` ### Escenario 3: Limitado por frecuencia ```python # Detection: 429 with Retry-After header # Recovery: Wait and retry, or switch to header auth def handle_rate_limit(response): retry_after = int(response.headers.get("Retry-After", 60)) print(f"Rate limited. Waiting {retry_after}s...") time.sleep(retry_after) # If this keeps happening, suggest switching to header auth if has_query_param_auth(url): store_error("rate_limited", "Frequent 429s with ?key= auth", "Switch to Authorization: Bearer header (no rate limit)") ``` ### Escenario 4: Error de servidor (5xx) ```python # Detection: 500, 502, 503 # Recovery: Retry with backoff, check /health def handle_server_error(url): # Check if server is up health = requests.get(f"{URL}/health") if health.status_code != 200: store_error("server_down", "Synapse health check failing", "Wait for server recovery") raise ServerDownError() # Retry with backoff return call_with_retry(url, max_retries=5) ``` ### Escenario 5: La llamada a herramienta falla ```python # Detection: Tool returns error content # Recovery: Try alternative approach, store failure def call_tool_safely(tool_name, args, alternatives=None): try: result = call_tool(tool_name, args) if result.get("isError"): raise ToolError(result["content"]) return result except ToolError as e: store_error(f"tool_{tool_name}_failed", f"Args: {args}\nError: {e}", f"Try: {alternatives or 'no alternatives'}") # Try alternatives if alternatives: for alt in alternatives: try: return call_tool(alt, args) except: continue raise ``` ## Patrón: Circuit Breaker Para fallos repetidos, deje de intentarlo temporalmente: ```python class CircuitBreaker: def __init__(self, threshold=5, reset_time=300): self.failures = 0 self.threshold = threshold self.reset_time = reset_time self.last_failure = 0 def call(self, fn, *args, **kwargs): if self.failures >= self.threshold: if time.time() - self.last_failure < self.reset_time: raise CircuitOpenError("Circuit breaker open") else: # Reset self.failures = 0 try: result = fn(*args, **kwargs) self.failures = 0 # Reset on success return result except: self.failures += 1 self.last_failure = time.time() raise # Usage breaker = CircuitBreaker(threshold=5) try: result = breaker.call(api_call, url) except CircuitOpenError: print("Too many failures, waiting before retry") ``` ## Mejores prácticas > [!TIP] > - **Reintente siempre los errores transitorios** — las redes fallan, los servidores tienen hipo > - **No reintente los errores de cliente (4xx)** — no se arreglarán solos > - **Almacene errores como memorias** — aprenda de los patrones > - **Notifique a los humanos los errores críticos** — necesitan saber > - **Degrade de forma elegante** — un trabajo parcial es mejor que un bloqueo > - **Use circuit breakers** — no martillee un servicio que está fallando ## Próximos pasos - [Referencia de la API de errores](/docs/api/errors) - [Patrón de inicio de sesión](/docs/llm-cookbook/session-start-pattern) - [Tests autoreparables](/docs/guides/self-healing-tests)