interface ModelProvider {
  readonly providerId: string;
  readonly modelId: string;
  generate(messages: ChatMessage[], options?: ModelConfig & { tools?: ToolDefinition[] }): Promise<ModelResponse>;
  stream(messages: ChatMessage[], options?: ModelConfig & { tools?: ToolDefinition[] }): AsyncGenerator<StreamChunk>;
}

import {
  Agent, openai, anthropic, google, vertex, ollama,
  awsBedrock, awsClaude, azureOpenai, azureFoundry,
  deepseek, mistral, xai, perplexity, cohere, meta, vercel,
} from "@agentium/core";

// OpenAI
const model = openai("gpt-4o");

// Anthropic
const model = anthropic("claude-sonnet-4-20250514");

// Google Gemini (API key)
const model = google("gemini-2.5-flash");

// Google Vertex AI (GCP auth)
const model = vertex("gemini-2.5-flash", { project: "my-project" });

// Local Ollama (no API key)
const model = ollama("llama3.1");

// AWS Bedrock (Mistral, Nova, Llama, etc.)
const model = awsBedrock("mistral.mistral-large-2402-v1:0");

// AWS Claude (Claude via Bedrock)
const model = awsClaude("us.anthropic.claude-sonnet-4-20250514-v1:0");

// Azure OpenAI (GPT on Azure)
const model = azureOpenai("gpt-4o");

// Azure AI Foundry (Phi, Llama, Mistral on Azure)
const model = azureFoundry("Phi-4");

// DeepSeek (reasoning + chat)
const model = deepseek("deepseek-chat");

// Mistral (code, vision, reasoning)
const model = mistral("mistral-large-latest");

// xAI Grok
const model = xai("grok-3");

// Perplexity (built-in web search)
const model = perplexity("sonar-pro");

// Cohere (RAG-optimized)
const model = cohere("command-r-plus");

// Meta Llama (via Llama API)
const model = meta("Llama-4-Scout-17B-16E-Instruct");

// Vercel v0 (web dev code gen)
const model = vercel("v0-1.0-md");

const agent = new Agent({
  name: "Assistant",
  model,
  instructions: "You are a helpful assistant.",
});

import { VoiceAgent, openaiRealtime, googleLive } from "@agentium/core";

// OpenAI Realtime
const agent = new VoiceAgent({
  name: "assistant",
  provider: openaiRealtime("gpt-4o-realtime-preview"),
});

// Google Gemini Live
const agent = new VoiceAgent({
  name: "assistant",
  provider: googleLive("gemini-2.5-flash-native-audio-preview-12-2025"),
});

const response = await model.generate(messages, {
  temperature: 0.3,
  maxTokens: 1024,
  responseFormat: "json",
});

interface TokenUsage {
  promptTokens: number;
  completionTokens: number;
  totalTokens: number;
  reasoningTokens?: number;
  cachedTokens?: number;
  audioInputTokens?: number;
  audioOutputTokens?: number;
  providerMetrics?: Record<string, unknown>;
}

const result = await agent.run("Hello!");

console.log(result.usage.promptTokens);       // 16 (normalized)
console.log(result.usage.providerMetrics);     // Raw API response
// OpenAI: { prompt_tokens: 16, completion_tokens: 10, ... }
// Vertex: { promptTokenCount: 16, candidatesTokenCount: 10, thoughtsTokenCount: 0, ... }