pages/api/chat.ts

import type { NextApiRequest, NextApiResponse } from 'next'
import OpenAI from 'openai'

export const config = {
  api: {
    responseLimit: false,
  },
}

export default async function handler(
  req: NextApiRequest,
  res: NextApiResponse
) {
  if (req.method !== 'POST') {
    return res.status(405).json({ error: 'Method not allowed' })
  }

  const hfToken = process.env.HF_TOKEN
  if (!hfToken) {
    return res.status(500).json({ error: 'HF_TOKEN not configured' })
  }

  const { messages } = req.body
  if (!messages || !Array.isArray(messages)) {
    return res.status(400).json({ error: 'Invalid messages format' })
  }

  const openai = new OpenAI({
    baseURL: 'https://router.huggingface.co/v1',
    apiKey: hfToken,
  })

  try {
    const stream = await openai.chat.completions.create({
      model: 'zai-org/GLM-4.6V-Flash:zai-org',
      messages,
      stream: true,
      max_tokens: 1024,
    })

    res.setHeader('Content-Type', 'text/plain; charset=utf-8')
    res.setHeader('Cache-Control', 'no-cache')
    res.setHeader('Connection', 'keep-alive')

    for await (const chunk of stream) {
      const content = chunk.choices[0]?.delta?.content || ''
      res.write(content)
    }

    res.end()
  } catch (error) {
    console.error('API error:', error)
    res.status(500).json({ error: 'Failed to generate response' })
  }
}