Byted Podcast Gen

                                 Apache License
                           Version 2.0, January 2004
                        http://www.apache.org/licenses/
   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
   1. Definitions.
      "License" shall mean the terms and conditions for use, reproduction,
      and distribution as defined by Sections 1 through 9 of this document.
      "Licensor" shall mean the copyright owner or entity authorized by
      the copyright owner that is granting the License.
      "Legal Entity" shall mean the union of the acting entity and all
      other entities that control, are controlled by, or are under common
      control with that entity. For the purposes of this definition,
      "control" means (i) the power, direct or indirect, to cause the
      direction or management of such entity, whether by contract or
      otherwise, or (ii) ownership of fifty percent (50%) or more of the
      outstanding shares, or (iii) beneficial ownership of such entity.
      "You" (or "Your") shall mean an individual or Legal Entity
      exercising permissions granted by this License.
      "Source" form shall mean the preferred form for making modifications,
      including but not limited to software source code, documentation
      source, and configuration files.
      "Object" form shall mean any form resulting from mechanical
      transformation or translation of a Source form, including but
      not limited to compiled object code, generated documentation,
      and conversions to other media types.
      "Work" shall mean the work of authorship, whether in Source or
      Object form, made available under the License, as indicated by a
      copyright notice that is included in or attached to the work
      (an example is provided in the Appendix below).
      "Derivative Works" shall mean any work, whether in Source or Object
      form, that is based on (or derived from) the Work and for which the
      editorial revisions, annotations, elaborations, or other modifications
      represent, as a whole, an original work of authorship. For the purposes
      of this License, Derivative Works shall not include works that remain
      separable from, or merely link (or bind by name) to the interfaces of,
      the Work and Derivative Works thereof.
      "Contribution" shall mean any work of authorship, including
      the original version of the Work and any modifications or additions
      to that Work or Derivative Works thereof, that is intentionally
      submitted to Licensor for inclusion in the Work by the copyright owner
      or by an individual or Legal Entity authorized to submit on behalf of
      the copyright owner. For the purposes of this definition, "submitted"
      means any form of electronic, verbal, or written communication sent
      to the Licensor or its representatives, including but not limited to
      communication on electronic mailing lists, source code control systems,
      and issue tracking systems that are managed by, or on behalf of, the
      Licensor for the purpose of discussing and improving the Work, but
      excluding communication that is conspicuously marked or otherwise
      designated in writing by the copyright owner as "Not a Contribution."
      "Contributor" shall mean Licensor and any individual or Legal Entity
      on behalf of whom a Contribution has been received by Licensor and
      subsequently incorporated within the Work.
   2. Grant of Copyright License. Subject to the terms and conditions of
      this License, each Contributor hereby grants to You a perpetual,
      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
      copyright license to reproduce, prepare Derivative Works of,
      publicly display, publicly perform, sublicense, and distribute the
      Work and such Derivative Works in Source or Object form.
   3. Grant of Patent License. Subject to the terms and conditions of
      this License, each Contributor hereby grants to You a perpetual,
      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
      (except as stated in this section) patent license to make, have made,
      use, offer to sell, sell, import, and otherwise transfer the Work,
      where such license applies only to those patent claims licensable
      by such Contributor that are necessarily infringed by their
      Contribution(s) alone or by combination of their Contribution(s)
      with the Work to which such Contribution(s) was submitted. If You
      institute patent litigation against any entity (including a
      cross-claim or counterclaim in a lawsuit) alleging that the Work
      or a Contribution incorporated within the Work constitutes direct
      or contributory patent infringement, then any patent licenses
      granted to You under this License for that Work shall terminate
      as of the date such litigation is filed.
   4. Redistribution. You may reproduce and distribute copies of the
      Work or Derivative Works thereof in any medium, with or without
      modifications, and in Source or Object form, provided that You
      meet the following conditions:
      (a) You must give any other recipients of the Work or
          Derivative Works a copy of this License; and
      (b) You must cause any modified files to carry prominent notices
          stating that You changed the files; and
      (c) You must retain, in the Source form of any Derivative Works
          that You distribute, all copyright, patent, trademark, and
          attribution notices from the Source form of the Work,
          excluding those notices that do not pertain to any part of
          the Derivative Works; and
      (d) If the Work includes a "NOTICE" text file as part of its
          distribution, then any Derivative Works that You distribute must
          include a readable copy of the attribution notices contained
          within such NOTICE file, excluding those notices that do not
          pertain to any part of the Derivative Works, in at least one
          of the following places: within a NOTICE text file distributed
          as part of the Derivative Works; within the Source form or
          documentation, if provided along with the Derivative Works; or,
          within a display generated by the Derivative Works, if and
          wherever such third-party notices normally appear. The contents
          of the NOTICE file are for informational purposes only and
          do not modify the License. You may add Your own attribution
          notices within Derivative Works that You distribute, alongside
          or as an addendum to the NOTICE text from the Work, provided
          that such additional attribution notices cannot be construed
          as modifying the License.
      You may add Your own copyright statement to Your modifications and
      may provide additional or different license terms and conditions
      for use, reproduction, or distribution of Your modifications, or
      for any such Derivative Works as a whole, provided Your use,
      reproduction, and distribution of the Work otherwise complies with
      the conditions stated in this License.
   5. Submission of Contributions. Unless You explicitly state otherwise,
      any Contribution intentionally submitted for inclusion in the Work
      by You to the Licensor shall be under the terms and conditions of
      this License, without any additional terms or conditions.
      Notwithstanding the above, nothing herein shall supersede or modify
      the terms of any separate license agreement you may have executed
      with Licensor regarding such Contributions.
   6. Trademarks. This License does not grant permission to use the trade
      names, trademarks, service marks, or product names of the Licensor,
      except as required for reasonable and customary use in describing the
      origin of the Work and reproducing the content of the NOTICE file.
   7. Disclaimer of Warranty. Unless required by applicable law or
      agreed to in writing, Licensor provides the Work (and each
      Contributor provides its Contributions) on an "AS IS" BASIS,
      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
      implied, including, without limitation, any warranties or conditions
      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
      PARTICULAR PURPOSE. You are solely responsible for determining the
      appropriateness of using or redistributing the Work and assume any
      risks associated with Your exercise of permissions under this License.
   8. Limitation of Liability. In no event and under no legal theory,
      whether in tort (including negligence), contract, or otherwise,
      unless required by applicable law (such as deliberate and grossly
      negligent acts) or agreed to in writing, shall any Contributor be
      liable to You for damages, including any direct, indirect, special,
      incidental, or consequential damages of any character arising as a
      result of this License or out of the use or inability to use the
      Work (including but not limited to damages for loss of goodwill,
      work stoppage, computer failure or malfunction, or any and all
      other commercial damages or losses), even if such Contributor
      has been advised of the possibility of such damages.
   9. Accepting Warranty or Additional Liability. While redistributing
      the Work or Derivative Works thereof, You may choose to offer,
      and charge a fee for, acceptance of support, warranty, indemnity,
      or other liability obligations and/or rights consistent with this
      License. However, in accepting such obligations, You may act only
      on Your own behalf and on Your sole responsibility, not on behalf
      of any other Contributor, and only if You agree to indemnify,
      defend, and hold each Contributor harmless for any liability
      incurred by, or claims asserted against, such Contributor by reason
      of your accepting any such warranty or additional liability.

websockets>=12.0

import json
import os
import urllib.error
import urllib.request
from urllib.parse import parse_qsl, urlencode, urlparse, urlunparse


def _build_action_url(base: str, action: str, version: str = "2025-05-20") -> str:
    base = (base or "").strip()
    if not base:
        return ""
    parsed = urlparse(base)
    path = parsed.path or "/"
    if not path.endswith("/"):
        path = f"{path}/"
    query = dict(parse_qsl(parsed.query))
    query["Action"] = action
    query["Version"] = version
    return urlunparse(parsed._replace(path=path, query=urlencode(query)))


def _extract_json(text: str) -> dict | None:
    if not text:
        return None
    text = text.strip()
    try:
        return json.loads(text)
    except Exception:
        pass
    start = text.find("{")
    end = text.rfind("}")
    if start == -1 or end == -1 or end <= start:
        return None
    try:
        return json.loads(text[start : end + 1])
    except Exception:
        return None


def _post_json(url: str, headers: dict, payload: dict, timeout_s: int = 15) -> dict | None:
    if not url:
        return None
    data = json.dumps(payload, ensure_ascii=False).encode("utf-8")
    req = urllib.request.Request(url, data=data, method="POST")
    for k, v in (headers or {}).items():
        if v is None:
            continue
        req.add_header(k, v)
    try:
        with urllib.request.urlopen(req, timeout=timeout_s) as resp:
            body = resp.read().decode("utf-8", errors="replace")
            return _extract_json(body)
    except urllib.error.HTTPError as e:
        try:
            body = e.read().decode("utf-8", errors="replace")
            return _extract_json(body)
        except Exception:
            return None
    except Exception:
        return None


def _dotenv_path() -> str:
    return os.path.join(os.path.dirname(os.path.abspath(__file__)), ".env")


def _load_dotenv_if_available(dotenv_path: str) -> None:
    try:
        from dotenv import load_dotenv  # type: ignore
    except Exception:
        return
    try:
        load_dotenv(dotenv_path=dotenv_path, override=False)
    except Exception:
        return


def _persist_env_to_dotenv_if_available(dotenv_path: str, key: str, value: str) -> None:
    value = (value or "").strip()
    if not value:
        return
    try:
        from dotenv import set_key  # type: ignore
    except Exception:
        return
    try:
        os.makedirs(os.path.dirname(dotenv_path) or ".", exist_ok=True)
        set_key(dotenv_path, key, value, quote_mode="never")
        try:
            os.chmod(dotenv_path, 0o600)
        except Exception:
            pass
    except Exception:
        return


def get_speech_api_key(project_name: str = "default", create_name: str = "arkclaw") -> str:
    _load_dotenv_if_available(_dotenv_path())

    speech_key = os.getenv("MODEL_SPEECH_API_KEY", "").strip()
    if speech_key:
        return speech_key

    ark_key = os.getenv("ARK_SKILL_API_KEY", "").strip()
    base = os.getenv("ARK_SKILL_API_BASE", "").strip()
    if not ark_key or not base:
        return ""

    headers = {
        "ServiceName": "speech_saas_prod",
        "Authorization": f"Bearer {ark_key}",
        "Content-Type": "application/json",
    }

    list_url = _build_action_url(base, "ListAPIKeys")
    list_data = _post_json(
        list_url,
        headers=headers,
        payload={"ProjectName": project_name, "OnlyAvailable": True},
    )
    if isinstance(list_data, dict):
        api_keys = (list_data.get("Result") or {}).get("APIKeys") or []
        if isinstance(api_keys, list) and api_keys:
            first = api_keys[0] if isinstance(api_keys[0], dict) else {}
            first_key = (first.get("APIKey") or "").strip()
            if first_key:
                os.environ["MODEL_SPEECH_API_KEY"] = first_key
                _persist_env_to_dotenv_if_available(_dotenv_path(), "MODEL_SPEECH_API_KEY", first_key)
                return first_key

    create_url = _build_action_url(base, "CreateAPIKey")
    create_data = _post_json(
        create_url,
        headers=headers,
        payload={"ProjectName": project_name, "Name": create_name},
    )
    if isinstance(create_data, dict):
        created_key = ((create_data.get("Result") or {}).get("APIKey") or "").strip()
        if created_key:
            os.environ["MODEL_SPEECH_API_KEY"] = created_key
            _persist_env_to_dotenv_if_available(_dotenv_path(), "MODEL_SPEECH_API_KEY", created_key)
            return created_key

    return ""

# -*- coding: utf-8 -*-
import argparse
import asyncio
import json
import logging
import os
import sys
import uuid

import websockets

_SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
if _SCRIPT_DIR not in sys.path:
    sys.path.insert(0, _SCRIPT_DIR)

from api_key import get_speech_api_key
from protocols import (EventType, MsgType, finish_connection,  # noqa: E402
                       finish_session, receive_message, start_connection,
                       start_session, wait_for_event)

logging.basicConfig(level=logging.INFO)
logger = logging.getLogger("PodcastTTS")

ENDPOINT = "wss://openspeech.bytedance.com/api/v3/sami/podcasttts"


def _load_json_value(value: str):
    if value is None:
        return None
    value = value.strip()
    if not value:
        return None
    if os.path.exists(value):
        with open(value, "r", encoding="utf-8") as f:
            return json.load(f)
    return json.loads(value)


def _output_dir_from_output_path(output_path: str) -> str:
    if output_path:
        d = os.path.dirname(output_path)
        return d if d else "output"
    return "output"


def _final_extension(encoding: str) -> str:
    return "ogg" if encoding == "ogg_opus" else encoding


async def _generate(args) -> dict:
    api_key = get_speech_api_key()
    if not api_key:
        raise ValueError("Missing MODEL_SPEECH_API_KEY")
    resource_id ="volc.service_type.10050"
    endpoint = ENDPOINT
    return_audio_url = True
    skip_round_audio_save = True

    if args.action == 0 and not (args.text or args.input_url):
        raise ValueError("action=0 requires --text or --input_url")
    if args.action == 3 and not args.nlp_texts:
        raise ValueError("action=3 requires --nlp_texts")
    if args.action == 4 and not args.prompt_text:
        raise ValueError("action=4 requires --prompt_text")

    headers = {
        "X-Api-Key": api_key,
        "X-Api-Resource-Id": resource_id,
        "X-Api-Connect-Id": str(uuid.uuid4()),
    }

    output_dir = _output_dir_from_output_path(args.output)
    os.makedirs(output_dir, exist_ok=True)

    task_id = str(uuid.uuid4())
    session_id = str(uuid.uuid4())

    speaker_info = _load_json_value(args.speaker_info) if args.speaker_info else None
    nlp_texts = _load_json_value(args.nlp_texts) if args.nlp_texts else None

    req_params = {
        "input_id": args.input_id,
        "input_text": args.text,
        "nlp_texts": nlp_texts,
        "prompt_text": args.prompt_text,
        "action": args.action,
        "use_head_music": args.use_head_music,
        "use_tail_music": args.use_tail_music,
        "aigc_watermark": args.aigc_watermark,
        "input_info": {
            "input_url": args.input_url,
            "return_audio_url": return_audio_url,
            "only_nlp_text": args.only_nlp_text,
        },
        "speaker_info": speaker_info,
        "audio_config": {
            "format": args.encoding,
            "sample_rate": 24000,
            "speech_rate": 0,
        },
    }

    podcast_audio = bytearray()
    round_audio = bytearray()
    podcast_texts = []
    audio_received = False
    current_round = 0
    current_speaker = "speaker"
    podcast_end_payload = None

    async with websockets.connect(endpoint, additional_headers=headers) as websocket:
        await start_connection(websocket)
        await wait_for_event(websocket, MsgType.FullServerResponse, EventType.ConnectionStarted)

        await start_session(websocket, json.dumps(req_params, ensure_ascii=False).encode("utf-8"), session_id)
        await wait_for_event(websocket, MsgType.FullServerResponse, EventType.SessionStarted)
        await finish_session(websocket, session_id)

        while True:
            msg = await receive_message(websocket)

            if msg.type == MsgType.AudioOnlyServer and msg.event == EventType.PodcastRoundResponse:
                if msg.payload:
                    audio_received = True
                    round_audio.extend(msg.payload)
                continue

            if msg.type == MsgType.Error:
                raise RuntimeError(msg.payload.decode("utf-8", errors="replace"))

            if msg.type == MsgType.FullServerResponse:
                if msg.event == EventType.PodcastRoundStart:
                    data = json.loads(msg.payload.decode("utf-8", errors="replace"))
                    if data.get("text"):
                        podcast_texts.append({"text": data.get("text"), "speaker": data.get("speaker")})
                    current_speaker = data.get("speaker") or "speaker"
                    current_round = data.get("round_id") if data.get("round_id") is not None else 0
                    continue

                if msg.event == EventType.PodcastRoundEnd:
                    data = json.loads(msg.payload.decode("utf-8", errors="replace"))
                    if data.get("is_error"):
                        raise RuntimeError(json.dumps(data, ensure_ascii=False))
                    if round_audio:
                        if not skip_round_audio_save:
                            round_path = os.path.join(
                                output_dir,
                                f"{current_speaker}_{current_round}.{_final_extension(args.encoding)}",
                            )
                            with open(round_path, "wb") as f:
                                f.write(round_audio)
                        podcast_audio.extend(round_audio)
                        round_audio.clear()
                    continue

                if msg.event == EventType.PodcastEnd:
                    podcast_end_payload = json.loads(msg.payload.decode("utf-8", errors="replace"))
                    continue

            if msg.event == EventType.SessionFinished:
                break

        await finish_connection(websocket)
        await wait_for_event(websocket, MsgType.FullServerResponse, EventType.ConnectionFinished)

    result = {"status": "success", "task_id": session_id, "encoding": args.encoding}

    if podcast_texts:
        result["texts"] = json.dumps(podcast_texts, ensure_ascii=False, indent=2)

    if args.only_nlp_text:
        return result

    if not audio_received:
        raise RuntimeError("No audio data received")

    if podcast_audio:
        audio_path = args.output or os.path.join(output_dir, f"podcast_{session_id}.{_final_extension(args.encoding)}")
        with open(audio_path, "wb") as f:
            f.write(podcast_audio)
        result["audio_path"] = audio_path

    if return_audio_url and isinstance(podcast_end_payload, dict):
        audio_url = podcast_end_payload.get("meta_info", {}).get("audio_url")
        if audio_url:
            result["audio_url"] = audio_url

    return result


def _build_parser() -> argparse.ArgumentParser:
    parser = argparse.ArgumentParser()
    parser.add_argument("--action", default=4, type=int, choices=[0,4], help="Podcast type")
    parser.add_argument("--text", default="", help="Input text (action=0)")
    parser.add_argument("--input_url", default="", help="Input text URL (action=0)")
    parser.add_argument("--nlp_texts", default="", help="NLP texts JSON string or JSON file path (action=3)")
    parser.add_argument("--prompt_text", default="", help="Prompt text (action=4)")

    parser.add_argument("--encoding", default="mp3", choices=["mp3", "wav", "ogg_opus"], help="Audio format")
    parser.add_argument("--input_id", default="podcast_input", help="Unique input identifier")
    parser.add_argument("--speaker_info", default='{"random_order":false}', help="Speaker info JSON")

    parser.add_argument("--use_head_music", action="store_true", help="Enable head music")
    parser.add_argument("--use_tail_music", action="store_true", help="Enable tail music")
    parser.add_argument("--aigc_watermark", action="store_true", help="Enable aigc watermark")
    parser.add_argument("--only_nlp_text", action="store_true", help="Only output podcast texts")

    parser.add_argument("--output", default="", help="Final audio output path")
    parser.add_argument("--texts_output", default="", help="Podcast texts output path")
    return parser


def main() -> int:
    args = _build_parser().parse_args()
    try:
        result = asyncio.run(_generate(args))
        print(json.dumps(result, ensure_ascii=False))
        return 0
    except Exception as e:
        print(json.dumps({"status": "error", "error": str(e)}, ensure_ascii=False))
        return 1


if __name__ == "__main__":
    raise SystemExit(main())

from .protocols import (
    CompressionBits,
    EventType,
    HeaderSizeBits,
    Message,
    MsgType,
    MsgTypeFlagBits,
    SerializationBits,
    VersionBits,
    audio_only_client,
    cancel_session,
    finish_connection,
    finish_session,
    full_client_request,
    receive_message,
    start_connection,
    start_session,
    task_request,
    wait_for_event,
)

__all__ = [
    "CompressionBits",
    "EventType",
    "HeaderSizeBits",
    "Message",
    "MsgType",
    "MsgTypeFlagBits",
    "SerializationBits",
    "VersionBits",
    "audio_only_client",
    "cancel_session",
    "finish_connection",
    "finish_session",
    "full_client_request",
    "receive_message",
    "start_connection",
    "start_session",
    "task_request",
    "wait_for_event",
]

import io
import logging
import struct
from dataclasses import dataclass
from enum import IntEnum
from typing import Callable, List

import websockets

logger = logging.getLogger(__name__)


class MsgType(IntEnum):
    """Message type enumeration"""

    Invalid = 0
    FullClientRequest = 0b1
    AudioOnlyClient = 0b10
    FullServerResponse = 0b1001
    AudioOnlyServer = 0b1011
    FrontEndResultServer = 0b1100
    Error = 0b1111

    # Alias
    ServerACK = AudioOnlyServer

    def __str__(self) -> str:
        return self.name if self.name else f"MsgType({self.value})"


class MsgTypeFlagBits(IntEnum):
    """Message type flag bits"""

    NoSeq = 0  # Non-terminal packet with no sequence
    PositiveSeq = 0b1  # Non-terminal packet with sequence > 0
    LastNoSeq = 0b10  # Last packet with no sequence
    NegativeSeq = 0b11  # Last packet with sequence < 0
    WithEvent = 0b100  # Payload contains event number (int32)


class VersionBits(IntEnum):
    """Version bits"""

    Version1 = 1
    Version2 = 2
    Version3 = 3
    Version4 = 4


class HeaderSizeBits(IntEnum):
    """Header size bits"""

    HeaderSize4 = 1
    HeaderSize8 = 2
    HeaderSize12 = 3
    HeaderSize16 = 4


class SerializationBits(IntEnum):
    """Serialization method bits"""

    Raw = 0
    JSON = 0b1
    Thrift = 0b11
    Custom = 0b1111


class CompressionBits(IntEnum):
    """Compression method bits"""

    None_ = 0
    Gzip = 0b1
    Custom = 0b1111


class EventType(IntEnum):
    """Event type enumeration"""

    None_ = 0  # Default event

    # 1 ~ 49 Upstream Connection events
    StartConnection = 1
    StartTask = 1  # Alias of StartConnection
    FinishConnection = 2
    FinishTask = 2  # Alias of FinishConnection

    # 50 ~ 99 Downstream Connection events
    ConnectionStarted = 50  # Connection established successfully
    TaskStarted = 50  # Alias of ConnectionStarted
    ConnectionFailed = 51  # Connection failed (possibly due to authentication failure)
    TaskFailed = 51  # Alias of ConnectionFailed
    ConnectionFinished = 52  # Connection ended
    TaskFinished = 52  # Alias of ConnectionFinished

    # 100 ~ 149 Upstream Session events
    StartSession = 100
    CancelSession = 101
    FinishSession = 102

    # 150 ~ 199 Downstream Session events
    SessionStarted = 150
    SessionCanceled = 151
    SessionFinished = 152
    SessionFailed = 153
    UsageResponse = 154  # Usage response
    ChargeData = 154  # Alias of UsageResponse

    # 200 ~ 249 Upstream general events
    TaskRequest = 200
    UpdateConfig = 201

    # 250 ~ 299 Downstream general events
    AudioMuted = 250

    # 300 ~ 349 Upstream TTS events
    SayHello = 300

    # 350 ~ 399 Downstream TTS events
    TTSSentenceStart = 350
    TTSSentenceEnd = 351
    TTSResponse = 352
    TTSEnded = 359
    PodcastRoundStart = 360
    PodcastRoundResponse = 361
    PodcastRoundEnd = 362
    PodcastEnd = 363

    # 450 ~ 499 Downstream ASR events
    ASRInfo = 450
    ASRResponse = 451
    ASREnded = 459

    # 500 ~ 549 Upstream dialogue events
    ChatTTSText = 500  # (Ground-Truth-Alignment) text for speech synthesis

    # 550 ~ 599 Downstream dialogue events
    ChatResponse = 550
    ChatEnded = 559

    # 650 ~ 699 Downstream dialogue events
    # Events for source (original) language subtitle
    SourceSubtitleStart = 650
    SourceSubtitleResponse = 651
    SourceSubtitleEnd = 652
    # Events for target (translation) language subtitle
    TranslationSubtitleStart = 653
    TranslationSubtitleResponse = 654
    TranslationSubtitleEnd = 655

    def __str__(self) -> str:
        return self.name if self.name else f"EventType({self.value})"


@dataclass
class Message:
    """Message object

    Message format:
    0                 1                 2                 3
    | 0 1 2 3 4 5 6 7 | 0 1 2 3 4 5 6 7 | 0 1 2 3 4 5 6 7 | 0 1 2 3 4 5 6 7 |
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
    |    Version      |   Header Size   |     Msg Type    |      Flags      |
    |   (4 bits)      |    (4 bits)     |     (4 bits)    |     (4 bits)    |
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
    | Serialization   |   Compression   |           Reserved                |
    |   (4 bits)      |    (4 bits)     |           (8 bits)                |
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
    |                                                                       |
    |                   Optional Header Extensions                          |
    |                     (if Header Size > 1)                              |
    |                                                                       |
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
    |                                                                       |
    |                           Payload                                     |
    |                      (variable length)                                |
    |                                                                       |
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
    """

    version: VersionBits = VersionBits.Version1
    header_size: HeaderSizeBits = HeaderSizeBits.HeaderSize4
    type: MsgType = MsgType.Invalid
    flag: MsgTypeFlagBits = MsgTypeFlagBits.NoSeq
    serialization: SerializationBits = SerializationBits.JSON
    compression: CompressionBits = CompressionBits.None_

    event: EventType = EventType.None_
    session_id: str = ""
    connect_id: str = ""
    sequence: int = 0
    error_code: int = 0

    payload: bytes = b""

    @classmethod
    def from_bytes(cls, data: bytes) -> "Message":
        """Create message object from bytes"""
        if len(data) < 3:
            raise ValueError(
                f"Data too short: expected at least 3 bytes, got {len(data)}"
            )

        type_and_flag = data[1]
        msg_type = MsgType(type_and_flag >> 4)
        flag = MsgTypeFlagBits(type_and_flag & 0b00001111)

        msg = cls(type=msg_type, flag=flag)
        msg.unmarshal(data)
        return msg

    def marshal(self) -> bytes:
        """Serialize message to bytes"""
        buffer = io.BytesIO()

        # Write header
        header = [
            (self.version << 4) | self.header_size,
            (self.type << 4) | self.flag,
            (self.serialization << 4) | self.compression,
        ]

        header_size = 4 * self.header_size
        if padding := header_size - len(header):
            header.extend([0] * padding)

        buffer.write(bytes(header))

        # Write other fields
        writers = self._get_writers()
        for writer in writers:
            writer(buffer)

        return buffer.getvalue()

    def unmarshal(self, data: bytes) -> None:
        """Deserialize message from bytes"""
        buffer = io.BytesIO(data)

        # Read version and header size
        version_and_header_size = buffer.read(1)[0]
        self.version = VersionBits(version_and_header_size >> 4)
        self.header_size = HeaderSizeBits(version_and_header_size & 0b00001111)

        # Skip second byte
        buffer.read(1)

        # Read serialization and compression methods
        serialization_compression = buffer.read(1)[0]
        self.serialization = SerializationBits(serialization_compression >> 4)
        self.compression = CompressionBits(serialization_compression & 0b00001111)

        # Skip header padding
        header_size = 4 * self.header_size
        read_size = 3
        if padding_size := header_size - read_size:
            buffer.read(padding_size)

        # Read other fields
        readers = self._get_readers()
        for reader in readers:
            reader(buffer)

        # Check for remaining data
        remaining = buffer.read()
        if remaining:
            raise ValueError(f"Unexpected data after message: {remaining}")

    def _get_writers(self) -> List[Callable[[io.BytesIO], None]]:
        """Get list of writer functions"""
        writers = []

        if self.flag == MsgTypeFlagBits.WithEvent:
            writers.extend([self._write_event, self._write_session_id])

        if self.type in [
            MsgType.FullClientRequest,
            MsgType.FullServerResponse,
            MsgType.FrontEndResultServer,
            MsgType.AudioOnlyClient,
            MsgType.AudioOnlyServer,
        ]:
            if self.flag in [MsgTypeFlagBits.PositiveSeq, MsgTypeFlagBits.NegativeSeq]:
                writers.append(self._write_sequence)
        elif self.type == MsgType.Error:
            writers.append(self._write_error_code)
        else:
            raise ValueError(f"Unsupported message type: {self.type}")

        writers.append(self._write_payload)
        return writers

    def _get_readers(self) -> List[Callable[[io.BytesIO], None]]:
        """Get list of reader functions"""
        readers = []

        if self.type in [
            MsgType.FullClientRequest,
            MsgType.FullServerResponse,
            MsgType.FrontEndResultServer,
            MsgType.AudioOnlyClient,
            MsgType.AudioOnlyServer,
        ]:
            if self.flag in [MsgTypeFlagBits.PositiveSeq, MsgTypeFlagBits.NegativeSeq]:
                readers.append(self._read_sequence)
        elif self.type == MsgType.Error:
            readers.append(self._read_error_code)
        else:
            raise ValueError(f"Unsupported message type: {self.type}")

        if self.flag == MsgTypeFlagBits.WithEvent:
            readers.extend(
                [self._read_event, self._read_session_id, self._read_connect_id]
            )

        readers.append(self._read_payload)
        return readers

    def _write_event(self, buffer: io.BytesIO) -> None:
        """Write event"""
        buffer.write(struct.pack(">i", self.event))

    def _write_session_id(self, buffer: io.BytesIO) -> None:
        """Write session ID"""
        if self.event in [
            EventType.StartConnection,
            EventType.FinishConnection,
            EventType.ConnectionStarted,
            EventType.ConnectionFailed,
        ]:
            return

        session_id_bytes = self.session_id.encode("utf-8")
        size = len(session_id_bytes)
        if size > 0xFFFFFFFF:
            raise ValueError(f"Session ID size ({size}) exceeds max(uint32)")

        buffer.write(struct.pack(">I", size))
        if size > 0:
            buffer.write(session_id_bytes)

    def _write_sequence(self, buffer: io.BytesIO) -> None:
        """Write sequence number"""
        buffer.write(struct.pack(">i", self.sequence))

    def _write_error_code(self, buffer: io.BytesIO) -> None:
        """Write error code"""
        buffer.write(struct.pack(">I", self.error_code))

    def _write_payload(self, buffer: io.BytesIO) -> None:
        """Write payload"""
        size = len(self.payload)
        if size > 0xFFFFFFFF:
            raise ValueError(f"Payload size ({size}) exceeds max(uint32)")

        buffer.write(struct.pack(">I", size))
        buffer.write(self.payload)

    def _read_event(self, buffer: io.BytesIO) -> None:
        """Read event"""
        event_bytes = buffer.read(4)
        if event_bytes:
            self.event = EventType(struct.unpack(">i", event_bytes)[0])

    def _read_session_id(self, buffer: io.BytesIO) -> None:
        """Read session ID"""
        if self.event in [
            EventType.StartConnection,
            EventType.FinishConnection,
            EventType.ConnectionStarted,
            EventType.ConnectionFailed,
            EventType.ConnectionFinished,
        ]:
            return

        size_bytes = buffer.read(4)
        if size_bytes:
            size = struct.unpack(">I", size_bytes)[0]
            if size > 0:
                session_id_bytes = buffer.read(size)
                if len(session_id_bytes) == size:
                    self.session_id = session_id_bytes.decode("utf-8")

    def _read_connect_id(self, buffer: io.BytesIO) -> None:
        """Read connection ID"""
        if self.event in [
            EventType.ConnectionStarted,
            EventType.ConnectionFailed,
            EventType.ConnectionFinished,
        ]:
            size_bytes = buffer.read(4)
            if size_bytes:
                size = struct.unpack(">I", size_bytes)[0]
                if size > 0:
                    self.connect_id = buffer.read(size).decode("utf-8")

    def _read_sequence(self, buffer: io.BytesIO) -> None:
        """Read sequence number"""
        sequence_bytes = buffer.read(4)
        if sequence_bytes:
            self.sequence = struct.unpack(">i", sequence_bytes)[0]

    def _read_error_code(self, buffer: io.BytesIO) -> None:
        """Read error code"""
        error_code_bytes = buffer.read(4)
        if error_code_bytes:
            self.error_code = struct.unpack(">I", error_code_bytes)[0]

    def _read_payload(self, buffer: io.BytesIO) -> None:
        """Read payload"""
        size_bytes = buffer.read(4)
        if size_bytes:
            size = struct.unpack(">I", size_bytes)[0]
            if size > 0:
                self.payload = buffer.read(size)

    def __str__(self) -> str:
        """String representation"""
        if self.type in [MsgType.AudioOnlyServer, MsgType.AudioOnlyClient]:
            if self.flag in [MsgTypeFlagBits.PositiveSeq, MsgTypeFlagBits.NegativeSeq]:
                return f"MsgType: {self.type}, EventType:{self.event}, Sequence: {self.sequence}, PayloadSize: {len(self.payload)}"
            return f"MsgType: {self.type}, EventType:{self.event}, PayloadSize: {len(self.payload)}"
        elif self.type == MsgType.Error:
            return f"MsgType: {self.type}, EventType:{self.event}, ErrorCode: {self.error_code}, Payload: {self.payload.decode('utf-8', 'ignore')}"
        else:
            if self.flag in [MsgTypeFlagBits.PositiveSeq, MsgTypeFlagBits.NegativeSeq]:
                return f"MsgType: {self.type}, EventType:{self.event}, Sequence: {self.sequence}, Payload: {self.payload.decode('utf-8', 'ignore')}"
            return f"MsgType: {self.type}, EventType:{self.event}, Payload: {self.payload.decode('utf-8', 'ignore')}"


async def receive_message(websocket: websockets.WebSocketClientProtocol) -> Message:
    """Receive message from websocket"""
    try:
        data = await websocket.recv()
        if isinstance(data, str):
            raise ValueError(f"Unexpected text message: {data}")
        elif isinstance(data, bytes):
            msg = Message.from_bytes(data)
            logger.info(f"Received: {msg}")
            return msg
        else:
            raise ValueError(f"Unexpected message type: {type(data)}")
    except Exception as e:
        logger.error(f"Failed to receive message: {e}")
        raise


async def wait_for_event(
    websocket: websockets.WebSocketClientProtocol,
    msg_type: MsgType,
    event_type: EventType,
) -> Message:
    """Wait for specific event"""
    while True:
        msg = await receive_message(websocket)
        if msg.type != msg_type or msg.event != event_type:
            raise ValueError(f"Unexpected message: {msg}")
        if msg.type == msg_type and msg.event == event_type:
            return msg


async def full_client_request(
    websocket: websockets.WebSocketClientProtocol, payload: bytes
) -> None:
    """Send full client message"""
    msg = Message(type=MsgType.FullClientRequest, flag=MsgTypeFlagBits.NoSeq)
    msg.payload = payload
    logger.info(f"Sending: {msg}")
    await websocket.send(msg.marshal())


async def audio_only_client(
    websocket: websockets.WebSocketClientProtocol, payload: bytes, flag: MsgTypeFlagBits
) -> None:
    """Send audio-only client message"""
    msg = Message(type=MsgType.AudioOnlyClient, flag=flag)
    msg.payload = payload
    logger.info(f"Sending: {msg}")
    await websocket.send(msg.marshal())


async def start_connection(websocket: websockets.WebSocketClientProtocol) -> None:
    """Start connection"""
    msg = Message(type=MsgType.FullClientRequest, flag=MsgTypeFlagBits.WithEvent)
    msg.event = EventType.StartConnection
    msg.payload = b"{}"
    logger.info(f"Sending: {msg}")
    await websocket.send(msg.marshal())


async def finish_connection(websocket: websockets.WebSocketClientProtocol) -> None:
    """Finish connection"""
    msg = Message(type=MsgType.FullClientRequest, flag=MsgTypeFlagBits.WithEvent)
    msg.event = EventType.FinishConnection
    msg.payload = b"{}"
    logger.info(f"Sending: {msg}")
    await websocket.send(msg.marshal())


async def start_session(
    websocket: websockets.WebSocketClientProtocol, payload: bytes, session_id: str
) -> None:
    """Start session"""
    msg = Message(type=MsgType.FullClientRequest, flag=MsgTypeFlagBits.WithEvent)
    msg.event = EventType.StartSession
    msg.session_id = session_id
    msg.payload = payload
    logger.info(f"Sending: {msg}")
    await websocket.send(msg.marshal())


async def finish_session(
    websocket: websockets.WebSocketClientProtocol, session_id: str
) -> None:
    """Finish session"""
    msg = Message(type=MsgType.FullClientRequest, flag=MsgTypeFlagBits.WithEvent)
    msg.event = EventType.FinishSession
    msg.session_id = session_id
    msg.payload = b"{}"
    logger.info(f"Sending: {msg}")
    await websocket.send(msg.marshal())


async def cancel_session(
    websocket: websockets.WebSocketClientProtocol, session_id: str
) -> None:
    """Cancel session"""
    msg = Message(type=MsgType.FullClientRequest, flag=MsgTypeFlagBits.WithEvent)
    msg.event = EventType.CancelSession
    msg.session_id = session_id
    msg.payload = b"{}"
    logger.info(f"Sending: {msg}")
    await websocket.send(msg.marshal())


async def task_request(
    websocket: websockets.WebSocketClientProtocol, payload: bytes, session_id: str
) -> None:
    """Send task request"""
    msg = Message(type=MsgType.FullClientRequest, flag=MsgTypeFlagBits.WithEvent)
    msg.event = EventType.TaskRequest
    msg.session_id = session_id
    msg.payload = payload
    logger.info(f"Sending: {msg}")
    await websocket.send(msg.marshal())