import json, sys, threading, time
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer

LOG = []


class H(BaseHTTPRequestHandler):
    def log_message(self, *a):
        pass

    def do_GET(self):
        body = json.dumps({"data": [{"id": "deepseek-flash"}, {"id": "deepseek-v4-pro"}]}).encode()
        self.send_response(200)
        self.send_header("Content-Type", "application/json")
        self.send_header("Content-Length", str(len(body)))
        self.end_headers()
        self.wfile.write(body)

    def do_POST(self):
        n = int(self.headers.get("Content-Length", 0))
        raw = self.rfile.read(n)
        try:
            LOG.append(json.loads(raw))
        except Exception:
            LOG.append({"_raw": raw[:200].decode("latin1")})
        self.send_response(200)
        self.send_header("Content-Type", "text/event-stream")
        self.end_headers()
        def ev(o):
            self.wfile.write(b"data: " + json.dumps(o).encode() + b"\n\n")
            self.wfile.flush()
        base = {"id": "x", "object": "chat.completion.chunk", "model": "deepseek-flash"}
        ev({**base, "choices": [{"index": 0, "delta": {"role": "assistant", "content": "reply-%d" % len(LOG)}}]})
        ev({**base, "choices": [{"index": 0, "delta": {}, "finish_reason": "stop"}],
            "usage": {"prompt_tokens": 10, "completion_tokens": 2, "total_tokens": 12}})
        self.wfile.write(b"data: [DONE]\n\n")
        self.wfile.flush()


def start():
    s = ThreadingHTTPServer(("127.0.0.1", 0), H)
    threading.Thread(target=s.serve_forever, daemon=True).start()
    return s, "http://127.0.0.1:%d/v1" % s.server_address[1]