"""A minimal OpenAI-compatible server standing in for the Cortex.0 runtime.

Cortex.0 itself needs ~45 GiB of RAM and a GPU, neither of which this machine
has. This server speaks the same protocol so the fusion code can be validated
for real: real HTTP, real SDK calls, real agent loop.
"""

from __future__ import annotations

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


class Handler(BaseHTTPRequestHandler):
    protocol_version = "HTTP/1.1"
    calls: list[dict] = []

    def log_message(self, *args):  # silence the default stderr noise
        pass

    def _send(self, code: int, payload: dict) -> None:
        body = json.dumps(payload).encode()
        self.send_response(code)
        self.send_header("Content-Type", "application/json")
        self.send_header("Content-Length", str(len(body)))
        self.end_headers()
        self.wfile.write(body)

    def do_GET(self):
        if self.path.rstrip("/").endswith("/models"):
            self._send(200, {"object": "list", "data": [{"id": "cortex0", "object": "model"}]})
        else:
            self._send(404, {"error": "not found"})

    def do_POST(self):
        length = int(self.headers.get("Content-Length", 0))
        request = json.loads(self.rfile.read(length) or b"{}")
        Handler.calls.append(request)
        messages = request.get("messages", [])
        tools = request.get("tools") or []

        # First turn: request a tool. Later turns: answer in plain text.
        already_acted = any(m.get("role") == "tool" for m in messages)
        if tools and not already_acted:
            self._send(200, {
                "id": "cmpl-1", "object": "chat.completion", "model": "cortex0",
                "choices": [{
                    "index": 0, "finish_reason": "tool_calls",
                    "message": {
                        "role": "assistant", "content": None,
                        "tool_calls": [{
                            "id": "call_1", "type": "function",
                            "function": {"name": tools[0]["function"]["name"],
                                         "arguments": json.dumps({"command": "echo cortex0-fused"})},
                        }],
                    },
                }],
                "usage": {"prompt_tokens": 10, "completion_tokens": 5, "total_tokens": 15},
            })
        else:
            self._send(200, {
                "id": "cmpl-2", "object": "chat.completion", "model": "cortex0",
                "choices": [{
                    "index": 0, "finish_reason": "stop",
                    "message": {"role": "assistant", "content": "Task complete."},
                }],
                "usage": {"prompt_tokens": 20, "completion_tokens": 4, "total_tokens": 24},
            })


def start(port: int = 0) -> tuple[ThreadingHTTPServer, str]:
    server = ThreadingHTTPServer(("127.0.0.1", port), Handler)
    threading.Thread(target=server.serve_forever, daemon=True).start()
    return server, f"http://127.0.0.1:{server.server_address[1]}/v1"