"""Xiaozhi WebSocket handshake frame models (PoC).

CON-004: the exact field set of the Xiaozhi ``hello`` frame is a firmware
detail. These models capture the fields the plan names (Device-Id,
Client-Id, Authorization, audio_params) plus the standard handshake fields.
Every constant that must match the firmware is marked ``# FIRMWARE``.
"""
from __future__ import annotations

import uuid
from typing import Any, Optional

from pydantic import BaseModel, Field


class AudioParams(BaseModel):
    # FIRMWARE: Opus params the device reports/accepts.
    format: str = "opus"
    sample_rate: int = 16000
    channels: int = 1
    frame_duration: int = 20  # ms


class Hello(BaseModel):
    """Device -> Bridge greeting (first text frame)."""
    type: str = "hello"
    device_id: str = ""
    client_id: Optional[str] = None
    authorization: Optional[str] = None  # FIRMWARE: token field name
    protocol_version: int = 1            # FIRMWARE
    audio_params: AudioParams = Field(default_factory=AudioParams)


class ServerHello(BaseModel):
    """Bridge -> Device acknowledgement, firmware v2.5.0-compatible.

    FIRMWARE: ParseServerHello requires ``transport == "websocket"`` and
    reads ``session_id`` + ``audio_params`` (sample_rate, frame_duration).
    """
    type: str = "hello"
    transport: str = "websocket"
    session_id: str = ""
    audio_params: AudioParams = Field(default_factory=AudioParams)
    server_time: int = 0


def build_hello(payload: dict) -> Hello:
    """Parse a raw hello dict; tolerate firmware field-name drift.

    Tolerant parsing is intentional: firmware builds differ, and the PoC must
    connect, not reject, on a missing optional field.
    """
    data: dict[str, Any] = dict(payload)
    data.setdefault("type", "hello")
    # Common firmware aliases.
    for src, dst in (("deviceId", "device_id"), ("Device-Id", "device_id")):
        if src in data and "device_id" not in data:
            data["device_id"] = data[src]
    if "audio" in data and "audio_params" not in data:
        data["audio_params"] = data.pop("audio")
    return Hello.model_validate(data)


def build_server_hello(device_hello: Hello) -> ServerHello:
    """Firmware-compatible server hello (transport=websocket + session_id)."""
    import time

    return ServerHello(
        session_id=str(uuid.uuid4()),
        audio_params=device_hello.audio_params,
        server_time=int(time.time() * 1000),
    )