Agent 错误恢复

错误总会发生。网络故障、API 返回 500、Mind Key 失效。本指南展示 LLM Agent 如何优雅地处理错误并从中学习。

错误处理原则

1. 退避重试 — 瞬时错误常常会自行恢复
2. 存储错误 — 从模式中学习
3. 优雅降级 — 不要让整个会话崩溃
4. 通知人类 — 对于无法解决的错误

HTTP 错误处理

指数退避重试

import time
import requests

def call_with_retry(url, max_retries=3, backoff_base=2):
    """带指数退避的 URL 调用。"""
    for attempt in range(max_retries):
        try:
            r = requests.get(url, headers={"Authorization": f"Bearer {KEY}"})
            
            # 成功
            if r.status_code < 400:
                return r
            
            # 限速 — 等待并重试
            if r.status_code == 429:
                wait = int(r.headers.get("Retry-After", 60))
                print(f"Rate limited. Waiting {wait}s...")
                time.sleep(wait)
                continue
            
            # 服务器错误 — 退避重试
            if r.status_code >= 500:
                wait = backoff_base ** attempt
                print(f"Server error {r.status_code}. Retrying in {wait}s...")
                time.sleep(wait)
                continue
            
            # 客户端错误 — 不重试
            if 400 <= r.status_code < 500:
                raise ClientError(f"{r.status_code}: {r.text}")
        
        except requests.RequestException as e:
            # 网络错误 — 重试
            wait = backoff_base ** attempt
            print(f"Network error: {e}. Retrying in {wait}s...")
            time.sleep(wait)
    
    raise MaxRetriesError(f"Failed after {max_retries} retries")

认证错误处理

def safe_call(url):
    """带认证错误处理的调用。"""
    try:
        return call_with_retry(url)
    except ClientError as e:
        if "401" in str(e):
            # Mind Key 无效 — 严重，无法恢复
            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):
            # 路径不存在 — 不重试
            store_error("not_found", str(e), "Check endpoint path")
            raise NotFoundError(str(e))
        else:
            raise

把错误存为记忆

发生错误时，存储它们以便未来会话学习：

def store_error(error_type, error_message, recovery_hint=""):
    """把错误存为记忆供未来参考。"""
    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"
        })

# 示例
try:
    deploy()
except DeployError as e:
    store_error("deploy_failed", str(e), 
                "Check CI logs, verify Docker image exists")
    raise

常见错误场景

场景 1：Mind Key 无效

# 检测：每次调用都返回 401
# 恢复：无法恢复 — 需要人类介入

def handle_invalid_mind_key():
    store_error("mind_key_invalid", 
                "All API calls returning 401",
                "Mind Key may be revoked. Need new key.")
    
    # 尽量通过聊天通知人类
    try:
        reply("⚠️ My Mind Key is invalid. I cannot access memories. "
              "Please check and update SYNAPSE_MIND_KEY.")
    except:
        pass  # 用坏 key 聊天也会失败
    
    # 优雅退出
    raise CriticalError("Cannot continue without valid Mind Key")

场景 2：网络错误

# 检测：ConnectionError、Timeout
# 恢复：退避重试，然后降级

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)
    
    # 所有重试失败 — 降级
    store_error("network_failure", 
                f"Cannot reach {url}",
                "Check internet connection, Synapse may be down")
    
    # 尽量离线工作
    return work_offline()

场景 3：被限速

# 检测：429 + Retry-After 头
# 恢复：等待后重试，或改用头部认证

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)
    
    # 如果频繁发生，建议改用头部认证
    if has_query_param_auth(url):
        store_error("rate_limited", 
                    "Frequent 429s with ?key= auth",
                    "Switch to Authorization: Bearer header (no rate limit)")

场景 4：服务器错误（5xx）

# 检测：500、502、503
# 恢复：退避重试，检查 /health

def handle_server_error(url):
    # 检查服务器是否在线
    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()
    
    # 退避重试
    return call_with_retry(url, max_retries=5)

场景 5：工具调用失败

# 检测：工具返回错误内容
# 恢复：尝试备选方案，存储失败

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'}")
        
        # 尝试备选方案
        if alternatives:
            for alt in alternatives:
                try:
                    return call_tool(alt, args)
                except:
                    continue
        
        raise

模式：熔断器

对于反复出现的失败，暂时停止尝试：

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:
                # 重置
                self.failures = 0
        
        try:
            result = fn(*args, **kwargs)
            self.failures = 0  # 成功时重置
            return result
        except:
            self.failures += 1
            self.last_failure = time.time()
            raise

# 用法
breaker = CircuitBreaker(threshold=5)
try:
    result = breaker.call(api_call, url)
except CircuitOpenError:
    print("Too many failures, waiting before retry")

最佳实践

下一步

• 错误 API 参考
• 会话启动模式
• 自愈测试