import { Agent, openai, EventBus, SessionProfiler, DEFAULT_ARCHITECTURES } from "@radaros/core";

const eventBus = new EventBus();

const profiler = new SessionProfiler({
  modelArch: DEFAULT_ARCHITECTURES["llama-3.1-70b"],
  kvWarningThresholdGb: 100,
});
profiler.attach(eventBus);

const agent = new Agent({
  name: "assistant",
  model: openai("gpt-4o"),
  eventBus,
});

// Run some sessions
await agent.run("Hello!", { sessionId: "s1" });
await agent.run("Tell me more", { sessionId: "s1" });
await agent.run("Quick question", { sessionId: "s2" });

// Get live stats
const stats = profiler.getSessionStats();
console.log(stats.byCategory);     // { light: 2, medium: 0, heavy: 0, extreme: 0 }
console.log(stats.totalTokens);    // actual token count from API
console.log(stats.estimatedKvGb);  // tokens × kvBytesPerToken

eventBus.on("capacity.session.classified", (data) => {
  console.log(`Session ${data.sessionId} → ${data.category}`);
  console.log(`Total tokens: ${data.totalTokens}`);
  console.log(`Previous: ${data.previousCategory}`);
});

eventBus.on("capacity.warning", (data) => {
  console.log(data.message);
  console.log(`KV: ${data.estimatedKvGb} GB`);
  console.log(`Sessions: ${data.sessionCount}`);
});

import { planCapacity, DEFAULT_GPU_SPECS } from "@radaros/core";

const mix = profiler.getWorkloadMix();
// → { extreme: 0, heavy: 1, medium: 2, light: 5 }

const plan = planCapacity(
  DEFAULT_ARCHITECTURES["llama-3.1-70b"],
  { gpu: DEFAULT_GPU_SPECS["h100-sxm"], gpuCount: 4, nandPerGpuGb: 0, nandBandwidthGBs: 7 },
  mix,     // real observed workload
  "fp8",
  "bf16",
);

console.log(`Need ${plan.hbmSlots} HBM slots for observed workload`);

radaros_session_category_total{category="light"} 5
radaros_session_category_total{category="heavy"} 1
radaros_capacity_sessions_total 6
radaros_kv_cache_estimated_gb 12.5