// 60-70% of queries can use sonar, saving 3-15x per query
function selectModel(query: string): "sonar" | "sonar-pro" {
  const simplePatterns = [
    /^what is/i, /^define/i, /^who is/i, /^when did/i,
    /current price/i, /^how many/i, /^is it true/i,
  ];
  if (simplePatterns.some((p) => p.test(query))) return "sonar";

  const complexPatterns = [
    /compare.*vs/i, /analysis of/i, /comprehensive/i,
    /pros and cons/i, /in-depth/i, /research/i,
  ];
  if (complexPatterns.some((p) => p.test(query))) return "sonar-pro";

  return "sonar"; // Default to cheapest
}

set -euo pipefail
# Factual queries need ~100 tokens, not 4096
# Setting max_tokens dramatically reduces output costs

# Simple fact: 100 tokens = $0.0001 output
curl -X POST https://api.perplexity.ai/chat/completions \
  -H "Authorization: Bearer $PERPLEXITY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sonar",
    "messages": [{"role": "user", "content": "Current population of Tokyo"}],
    "max_tokens": 100
  }'

# Research query: keep at 2048 only when needed
curl -X POST https://api.perplexity.ai/chat/completions \
  -H "Authorization: Bearer $PERPLEXITY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sonar-pro",
    "messages": [{"role": "user", "content": "Compare React vs Vue in 2025 for enterprise apps"}],
    "max_tokens": 2048
  }'

import { LRUCache } from "lru-cache";
import { createHash } from "crypto";

const searchCache = new LRUCache<string, any>({
  max: 10000,
  ttl: 4 * 3600_000, // 4-hour default TTL
});

async function cachedQuery(query: string, model: string) {
  const key = createHash("sha256")
    .update(`${model}:${query.toLowerCase().trim()}`)
    .digest("hex");

  const cached = searchCache.get(key);
  if (cached) return cached; // $0 cost

  const result = await perplexity.chat.completions.create({
    model,
    messages: [{ role: "user", content: query }],
  });
  searchCache.set(key, result);
  return result;
}

// Track cache effectiveness
function cacheStats() {
  return {
    size: searchCache.size,
    hitRate: `${((searchCache as any).hits / ((searchCache as any).hits + (searchCache as any).misses) * 100).toFixed(1)}%`,
  };
}

set -euo pipefail
# Restricting search domains = less content to process = lower request fee
curl -X POST https://api.perplexity.ai/chat/completions \
  -H "Authorization: Bearer $PERPLEXITY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sonar",
    "messages": [{"role": "user", "content": "Python 3.13 release notes"}],
    "search_domain_filter": ["python.org", "docs.python.org"],
    "max_tokens": 500
  }'

class CostTracker {
  private costs: Array<{ model: string; tokens: number; timestamp: Date }> = [];

  record(model: string, usage: { total_tokens: number }) {
    this.costs.push({
      model,
      tokens: usage.total_tokens,
      timestamp: new Date(),
    });
  }

  dailySummary() {
    const today = this.costs.filter(
      (c) => c.timestamp.toDateString() === new Date().toDateString()
    );
    const sonarTokens = today.filter((c) => c.model === "sonar").reduce((s, c) => s + c.tokens, 0);
    const proTokens = today.filter((c) => c.model === "sonar-pro").reduce((s, c) => s + c.tokens, 0);

    return {
      queries: today.length,
      estimatedCost: (sonarTokens * 0.000001) + (proTokens * 0.000009), // rough estimate
      sonarQueries: today.filter((c) => c.model === "sonar").length,
      proQueries: today.filter((c) => c.model === "sonar-pro").length,
    };
  }
}