snake-python/scripts/run_seeded_snake_tournament.py

#!/usr/bin/env python3
"""Run paired seeded games through the official local Battlesnake rules engine."""
import argparse
import json
import os
import re
import signal
import subprocess
import sys
import tempfile
import time
import urllib.error
import urllib.request
from collections import Counter
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
from threading import Thread
from pathlib import Path
from statistics import mean

ROOT = Path(__file__).resolve().parents[1]
ENGINE_USER_AGENT = "BattlesnakeEngine/local-tournament"
RESULT_RE = re.compile(
  r"Game completed after (\d+) turns\.(?: (.+?) was the winner\.| It was a draw\.)"
)

def wait_for_server(url: str, process: subprocess.Popen, timeout: float = 15.0) -> None:
  deadline = time.monotonic() + timeout
  while time.monotonic() < deadline:
    if process.poll() is not None:
      raise RuntimeError(f"Snake server exited with status {process.returncode}")
    try:
      with urllib.request.urlopen(url, timeout=0.5) as response:
        if response.status == 200:
          return
    except OSError:
      time.sleep(0.1)
  raise TimeoutError(f"Snake server did not become ready at {url}")

class _EngineHeaderProxy(BaseHTTPRequestHandler):
  target: str

  def do_GET(self) -> None:
    self._forward()

  def do_POST(self) -> None:
    self._forward()

  def _forward(self) -> None:
    length = int(self.headers.get("Content-Length", 0))
    body = self.rfile.read(length) if length else None
    request = urllib.request.Request(
      f"{self.target}{self.path}", data=body, method=self.command,
      headers={
        "Content-Type": self.headers.get("Content-Type", "application/json"),
        "User-Agent": ENGINE_USER_AGENT,
      },
    )
    try:
      with urllib.request.urlopen(request, timeout=2.0) as response:
        payload = response.read()
        self.send_response(response.status)
        self.send_header("Content-Type", response.headers.get("Content-Type", "application/json"))
    except urllib.error.HTTPError as error:
      payload = error.read()
      self.send_response(error.code)
      self.send_header("Content-Type", error.headers.get("Content-Type", "text/plain"))
    self.send_header("Content-Length", str(len(payload)))
    self.end_headers()
    self.wfile.write(payload)

  def log_message(self, format: str, *args) -> None:
    pass

def start_proxy(port: int, target_port: int) -> tuple[ThreadingHTTPServer, Thread]:
  handler = type(
    f"EngineHeaderProxy{port}",
    (_EngineHeaderProxy,),
    {"target": f"http://127.0.0.1:{target_port}"},
  )
  server = ThreadingHTTPServer(("127.0.0.1", port), handler)
  thread = Thread(target=server.serve_forever, daemon=True)
  thread.start()
  return server, thread

def start_server(snake: str, port: int) -> subprocess.Popen:
  env = os.environ.copy()
  env.update({
    "HOST": "127.0.0.1",
    "PORT": str(port),
    "SNAKE": snake,
    "DEBUG": "false",
    "DEBUG_SERVER": "false",
    "STORE_GAME_HISTORY": "false",
    "GAMEPLAY_DB_ENABLED": "false",
    "METRICS_CLEAR_WORKERS_ON_STARTUP": "false",
  })
  process = subprocess.Popen(
    [sys.executable, str(ROOT / "main.py")],
    cwd=ROOT,
    env=env,
    stdin=subprocess.DEVNULL,
    stdout=subprocess.DEVNULL,
    stderr=subprocess.DEVNULL,
    start_new_session=True,
  )
  wait_for_server(f"http://127.0.0.1:{port}", process)
  return process

def stop_server(process: subprocess.Popen) -> None:
  if process.poll() is not None:
    return
  os.killpg(process.pid, signal.SIGTERM)
  try:
    process.wait(timeout=5)
  except subprocess.TimeoutExpired:
    os.killpg(process.pid, signal.SIGKILL)
    process.wait(timeout=5)

def run_game(
  cli: Path,
  seed: int,
  game_type: str,
  map_name: str,
  players: list[tuple[str, str]],
  width: int,
  height: int,
  timeout_ms: int,
) -> dict:
  with tempfile.NamedTemporaryFile(prefix="snake-arena-", suffix=".jsonl") as output:
    command = [
      str(cli), "play", "-W", str(width), "-H", str(height),
      "-g", game_type, "--map", map_name, "--seed", str(seed),
      "--timeout", str(timeout_ms), "--output", output.name,
    ]
    for name, url in players:
      command.extend(("--name", name, "--url", url))
    completed = subprocess.run(
      command, cwd=ROOT, text=True, stdout=subprocess.PIPE,
      stderr=subprocess.STDOUT, timeout=180, check=False,
    )
    if completed.returncode != 0:
      raise RuntimeError(
        f"Rules engine failed for seed {seed}:\n{completed.stdout[-2000:]}"
      )
    output.seek(0)
    lines = [json.loads(line) for line in output if line.strip()]

  terminal = lines[-1] if lines else {}
  match = RESULT_RE.search(completed.stdout)
  turns = int(match.group(1)) if match else max(0, len(lines) - 2)
  winner = terminal.get("winnerName") or None
  draw = bool(terminal.get("isDraw", winner is None))
  return {"seed": seed, "winner": winner, "draw": draw, "turns": turns}

def main() -> None:
  parser = argparse.ArgumentParser()
  parser.add_argument("--games", type=int, default=20, help="Number of unique seeds")
  parser.add_argument("--seed-start", type=int, default=1)
  parser.add_argument("--gametype", default="standard")
  parser.add_argument("--map", default="standard")
  parser.add_argument("--width", type=int, default=11)
  parser.add_argument("--height", type=int, default=11)
  parser.add_argument("--timeout", type=int, default=500)
  parser.add_argument("--base-port", type=int, default=9301)
  parser.add_argument("--cli", default=str(ROOT / ".testing/tools/battlesnake-cli/battlesnake"))
  parser.add_argument("--json-output")
  args = parser.parse_args()

  cli = Path(args.cli)
  if not cli.is_file():
    raise SystemExit(f"Battlesnake CLI not found: {cli}. Run: just build-battlesnake-cli")

  apex_port, prism_port = args.base_port, args.base_port + 1
  apex_proxy_port, prism_proxy_port = args.base_port + 2, args.base_port + 3
  servers: list[subprocess.Popen] = []
  proxies: list[tuple[ThreadingHTTPServer, Thread]] = []
  results: list[dict] = []
  started = time.perf_counter()
  try:
    servers = [
      start_server("ApexBattleSnake", apex_port),
      start_server("PrismBattleSnake_GPT_5_6_Sol", prism_port),
    ]
    proxies = [
      start_proxy(apex_proxy_port, apex_port),
      start_proxy(prism_proxy_port, prism_port),
    ]
    urls = {
      "Apex": f"http://127.0.0.1:{apex_proxy_port}",
      "Prism": f"http://127.0.0.1:{prism_proxy_port}",
    }
    for offset in range(max(1, args.games)):
      seed = args.seed_start + offset
      # Swap engine slots for every seed. This controls for deterministic map
      # spawn positions and gives each strategy both initial placements.
      for order in (("Apex", "Prism"), ("Prism", "Apex")):
        result = run_game(
          cli=cli, seed=seed, game_type=args.gametype, map_name=args.map,
          players=[(name, urls[name]) for name in order],
          width=args.width, height=args.height, timeout_ms=args.timeout,
        )
        result["order"] = list(order)
        results.append(result)
        print(
          f"seed={seed} order={'/'.join(order)} winner={result['winner'] or 'draw'} "
          f"turns={result['turns']}"
        )
  finally:
    for proxy, thread in reversed(proxies):
      proxy.shutdown()
      proxy.server_close()
      thread.join(timeout=2)
    for server in reversed(servers):
      stop_server(server)

  wins = Counter(result["winner"] or "draw" for result in results)
  summary = {
    "games": len(results),
    "unique_seeds": max(1, args.games),
    "gametype": args.gametype,
    "map": args.map,
    "wins": dict(wins),
    "win_rates": {
      key: value / len(results) for key, value in wins.items()
    },
    "mean_turns": mean(result["turns"] for result in results),
    "elapsed_seconds": time.perf_counter() - started,
    "results": results,
  }
  print(json.dumps({key: value for key, value in summary.items() if key != "results"}, indent=2))
  if args.json_output:
    Path(args.json_output).write_text(json.dumps(summary, indent=2) + "\n")

if __name__ == "__main__":
  main()