"""Live smoke test against the running bridge (real WS, real auth, mock backends)."""
import asyncio
import json
import sys

import httpx
import websockets

BASE = "http://127.0.0.1:8766"
WS = "ws://127.0.0.1:8766/ws/xiaozhi"
TOKEN = "8a07643d106f9282a8f2eb1161da4f73657ce99b6602b98df89d011b8caf48a2"

results = {}

# 1. health
results["health"] = httpx.get(f"{BASE}/health", timeout=5).json()

# 2. bad token must be rejected
async def bad_token():
    async with websockets.connect(WS) as ws:
        await ws.send(json.dumps({
            "type": "hello",
            "device_id": "xiaozhi-main",
            "authorization": "wrong-token",
            "audio": {"format": "opus", "sample_rate": 16000, "channels": 1, "frame_duration": 20},
        }))
        return await ws.recv()

# 3. unknown device must be rejected
async def bad_device():
    async with websockets.connect(WS) as ws:
        await ws.send(json.dumps({
            "type": "hello",
            "device_id": "intruder",
            "authorization": TOKEN,
            "audio": {"format": "opus", "sample_rate": 16000, "channels": 1, "frame_duration": 20},
        }))
        return await ws.recv()

# 4. real handshake + a spoken turn
async def real_turn():
    frames = []
    audio_bytes = 0
    async with websockets.connect(WS) as ws:
        await ws.send(json.dumps({
            "type": "hello",
            "device_id": "xiaozhi-main",
            "client_id": "esp32-01",
            "authorization": TOKEN,
            "protocol_version": 1,
            "audio": {"format": "opus", "sample_rate": 16000, "channels": 1, "frame_duration": 20},
        }))
        for _ in range(20):
            data = await ws.recv()
            if isinstance(data, bytes):
                audio_bytes += len(data)
                frames.append("audio")
            else:
                frames.append(json.loads(data).get("type"))
                if frames[-1] == "hello":  # hello reply → session live
                    break
        # one spoken turn: 4800 bytes of PCM (0.15s @ 16k mono 16-bit)
        await ws.send(bytes(range(256)) * 19)
        got_text = False
        got_audio = False
        for _ in range(50):
            data = await ws.recv()
            if isinstance(data, bytes):
                got_audio = True
                audio_bytes += len(data)
            else:
                frames.append(json.loads(data).get("type"))
                if json.loads(data).get("type") == "text":
                    got_text = True
                    break
        # keep reading TTS audio chunks that follow the text
        while not got_audio:
            data = await ws.recv()
            if isinstance(data, bytes):
                got_audio = True
                audio_bytes += len(data)
            else:
                frames.append(json.loads(data).get("type"))
        return {"frames": frames, "audio_bytes": audio_bytes, "got_text": got_text, "got_audio_out": got_audio}

results["bad_token"] = asyncio.run(bad_token())
results["bad_device"] = asyncio.run(bad_device())
results["real_turn"] = asyncio.run(real_turn())

ok = (
    results["health"].get("status") == "ok"
    and json.loads(results["bad_token"]).get("type") == "error"
    and json.loads(results["bad_device"]).get("type") == "error"
    and results["real_turn"]["got_audio_out"]
)
print(json.dumps(results, ensure_ascii=False, indent=2))
print("LIVE SMOKE:", "PASS" if ok else "FAIL")
sys.exit(0 if ok else 1)