Rate Limiting & Backpressure

import { Agent, openai } from "@agentium/core";

const agent = new Agent({
  name: "rate-limited-agent",
  model: openai("gpt-4o"),
  rateLimit: {
    maxTokensPerMinute: 100_000,
    maxRequestsPerMinute: 60,
    maxConcurrent: 5,
    perTenant: true,
    onLimitReached: "degrade",
    degradeStrategy: {
      useCheaperModel: openai("gpt-4o-mini"),
      reduceMaxTokens: 1000,
    },
  },
});

import { TokenRateLimiter } from "@agentium/core";

const limiter = new TokenRateLimiter({
  maxTokensPerMinute: 100_000,
  maxTokensPerHour: 1_000_000,
  maxRequestsPerMinute: 60,
  perTenant: true,
  perUser: true,
});

// Check without consuming
const status = limiter.check({ tenantId: "acme", userId: "u1" });
// { allowed: true, remaining: 95000, resetMs: 45000 }

// Acquire tokens (pre-call estimate)
const result = limiter.acquire(500, { tenantId: "acme" });

// Reconcile after actual usage
limiter.record(actualTokens, estimatedTokens, { tenantId: "acme" });

import { ConcurrencyLimiter } from "@agentium/core";

const limiter = new ConcurrencyLimiter(5, 30_000); // max 5, 30s timeout

const release = await limiter.acquire();
try {
  await callLLM();
} finally {
  release();
}

console.log(limiter.active);    // current concurrent calls
console.log(limiter.pending);   // queued requests
console.log(limiter.available); // remaining capacity