██████╗ ███████╗███████╗██████╗ ███████╗███████╗███████╗██╗  ██╗
██╔══██╗██╔════╝██╔════╝██╔══██╗██╔════╝██╔════╝██╔════╝██║ ██╔╝
██║  ██║█████╗  █████╗  ██████╔╝███████╗█████╗  █████╗  █████╔╝
██║  ██║██╔══╝  ██╔══╝  ██╔═══╝ ╚════██║██╔══╝  ██╔══╝  ██╔═██╗
██████╔╝███████╗███████╗██║     ███████║███████╗███████╗██║  ██╗
╚═════╝ ╚══════╝╚══════╝╚═╝     ╚══════╝╚══════╝╚══════╝╚═╝  ╚═╝

npm install openai

import OpenAI from "openai";

const deepseek = new OpenAI({
  apiKey: process.env.DEEPSEEK_API_KEY!,
  baseURL: "https://api.deepseek.com",
});

const response = await deepseek.chat.completions.create({
  model: "deepseek-v4-flash",
  messages: [
    { role: "system", content: "You are a helpful assistant for codeAmani Labs." },
    { role: "user", content: "Summarize this M-Pesa transaction log." },
  ],
  max_tokens: 1024,
});

console.log(response.choices[0].message.content);

const response = await deepseek.chat.completions.create({
  model: "deepseek-v4-pro",
  messages: [
    { role: "user", content: "Why is my Supabase RLS policy blocking authenticated users?" },
  ],
  reasoning_effort: "high",
  // `thinking` is a DeepSeek extension not in the OpenAI types; the SDK forwards it.
  // @ts-expect-error — deepseek-specific field
  thinking: { type: "enabled" },
  max_tokens: 4096,
});

const choice = response.choices[0];
// @ts-expect-error — deepseek-specific field
console.log("Reasoning:", choice.message.reasoning_content);
console.log("Answer:", choice.message.content);

const stream = await deepseek.chat.completions.create({
  model: "deepseek-v4-flash",
  stream: true,
  messages: [{ role: "user", content: prompt }],
});

for await (const chunk of stream) {
  const delta = chunk.choices[0]?.delta?.content ?? "";
  process.stdout.write(delta);
}

// app/api/ai/deepseek/route.ts
import OpenAI from "openai";
import { NextRequest } from "next/server";

const deepseek = new OpenAI({
  apiKey: process.env.DEEPSEEK_API_KEY!,
  baseURL: "https://api.deepseek.com",
});

export async function POST(req: NextRequest) {
  const { messages } = await req.json();

  const stream = await deepseek.chat.completions.create({
    model: "deepseek-v4-flash",
    stream: true,
    messages,
  });

  const encoder = new TextEncoder();
  const readable = new ReadableStream({
    async start(controller) {
      for await (const chunk of stream) {
        const text = chunk.choices[0]?.delta?.content ?? "";
        if (text) controller.enqueue(encoder.encode(text));
      }
      controller.close();
    },
  });

  return new Response(readable, {
    headers: { "Content-Type": "text/plain; charset=utf-8" },
  });
}

// lib/ai.ts
type TaskComplexity = "high" | "medium" | "low";

function selectModel(complexity: TaskComplexity, requiresReasoning: boolean) {
  if (complexity === "high" || requiresReasoning) {
    return { provider: "anthropic", model: "claude-sonnet-4-6" };
  }
  if (complexity === "medium") {
    return { provider: "deepseek", model: "deepseek-v4-flash" };
  }
  // Low complexity: fast classification / simple Q&A
  return { provider: "anthropic", model: "claude-haiku-4-5-20251001" };
}

// lib/ai-resilient.ts
import OpenAI from "openai";
import Anthropic from "@anthropic-ai/sdk";

const deepseek = new OpenAI({
  apiKey: process.env.DEEPSEEK_API_KEY!,
  baseURL: "https://api.deepseek.com",
});

const anthropic = new Anthropic({ apiKey: process.env.ANTHROPIC_API_KEY! });

// Transient per DeepSeek docs: 429 (rate limit), 500 (server error), 503 (overloaded).
const RETRYABLE = new Set([429, 500, 503]);
const MAX_RETRIES = 3;

const sleep = (ms: number) => new Promise((r) => setTimeout(r, ms));

/**
 * Run a prompt through DeepSeek with exponential backoff on transient errors,
 * then fall back to Anthropic Claude if DeepSeek is unavailable or non-retryable.
 */
export async function completeWithFallback(prompt: string): Promise<string> {
  for (let attempt = 0; attempt <= MAX_RETRIES; attempt++) {
    try {
      const res = await deepseek.chat.completions.create({
        model: "deepseek-v4-flash",
        messages: [{ role: "user", content: prompt }],
        max_tokens: 2048,
      });
      return res.choices[0]?.message.content ?? "";
    } catch (err) {
      // OpenAI SDK surfaces the HTTP status on err.status
      const status = (err as { status?: number }).status;

      // Non-retryable (400/401/402/422) or out of attempts → break to fallback.
      if (!status || !RETRYABLE.has(status) || attempt === MAX_RETRIES) break;

      // Exponential backoff with full jitter: ~0.5s, 1s, 2s (+ jitter).
      const base = 500 * 2 ** attempt;
      await sleep(base + Math.random() * base);
    }
  }

  // Fallback tier — Anthropic Claude (consistent with lib/ai.ts router).
  const msg = await anthropic.messages.create({
    model: "claude-haiku-4-5-20251001",
    max_tokens: 2048,
    messages: [{ role: "user", content: prompt }],
  });
  const block = msg.content[0];
  return block.type === "text" ? block.text : "";
}

const response = await deepseek.chat.completions.create({
  model: "deepseek-v4-flash",
  response_format: { type: "json_object" },
  messages: [
    {
      role: "system",
      content: "Respond only with valid JSON.",
    },
    {
      role: "user",
      content: "Extract: name, amount, phone from this SMS: 'Confirmed. Ksh500 sent to 0712345678 on 12/5/26'",
    },
  ],
});

const data = JSON.parse(response.choices[0].message.content ?? "{}");
// { name: null, amount: 500, phone: "0712345678" }

# Required
DEEPSEEK_API_KEY=sk-...

# No separate base URL needed — set in code: https://api.deepseek.com