app.py

import os
from fastapi import FastAPI, HTTPException
from fastapi.responses import StreamingResponse, Response
from openai import AsyncOpenAI

app = FastAPI()

# Initialize global token
token = os.getenv("GITHUB_TOKEN")

async def generate_ai_response(prompt: str):
    global token
    if not token:
        raise HTTPException(status_code=500, detail="GitHub token not configured")
    
    endpoint = "https://models.github.ai/inference"
    model = "openai/gpt-4.1-mini"  # Unofficial model name

    client = AsyncOpenAI(base_url=endpoint, api_key=token)

    try:
        stream = await client.chat.completions.create(
            messages=[
                {"role": "system", "content": "You are a helpful assistant."},
                {"role": "user", "content": prompt}
            ],
            model=model,
            temperature=1.0,
            top_p=1.0,
            stream=True
        )

        async for chunk in stream:
            if chunk.choices and chunk.choices[0].delta.content:
                yield chunk.choices[0].delta.content

    except Exception as err:
        yield f"Error: {str(err)}"
        raise HTTPException(status_code=500, detail="AI generation failed")

class CustomStreamingResponse(Response):
    def __init__(self, content, token, media_type="text/event-stream", status_code=200):
        super().__init__(content=content, media_type=media_type, status_code=status_code)
        self.token = token

    async def __call__(self, scope, receive, send):
        await send({
            "type": "http.response.start",
            "status": self.status_code,
            "headers": [
                (b"content-type", self.media_type.encode()),
                (b"x-token-value", self.token.encode())
            ]
        })
        async for chunk in self.body_iterator:
            await send({
                "type": "http.response.body",
                "body": chunk.encode() if isinstance(chunk, str) else chunk,
                "more_body": True
            })
        await send({
            "type": "http.response.body",
            "body": b"",
            "more_body": False
        })

@app.post("/generate")
async def generate_response(prompt: str):
    if not prompt:
        raise HTTPException(status_code=400, detail="Prompt cannot be empty")
    
    global token
    return CustomStreamingResponse(
        content=generate_ai_response(prompt),
        token=token,
        media_type="text/event-stream"
    )

@app.get("/get-token")
async def get_token():
    global token
    if not token:
        raise HTTPException(status_code=500, detail="GitHub token not configured")
    return {"token": token}

def get_app():
    return app