LangBot/src/langbot/pkg/provider/runners/n8nsvapi.py

"""
Legacy n8n Service API Runner.

DEPRECATED: This runner has been migrated to the AgentRunner plugin format.
Use the official `langbot/n8n-agent` plugin instead.
"""

from __future__ import annotations

import typing
import json
import uuid
import aiohttp

from langbot.pkg.utils import httpclient

from .. import runner
from ...core import app
import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
import langbot_plugin.api.entities.builtin.provider.message as provider_message


class N8nAPIError(Exception):
    """N8n API 请求失败"""

    def __init__(self, message: str):
        self.message = message
        super().__init__(self.message)


@runner.runner_class('n8n-service-api')
class N8nServiceAPIRunner(runner.RequestRunner):
    """N8n Service API 工作流请求器"""

    def __init__(self, ap: app.Application, pipeline_config: dict):
        self.ap = ap
        self.pipeline_config = pipeline_config

        # 获取webhook URL
        self.webhook_url = self.pipeline_config['ai']['n8n-service-api']['webhook-url']

        # 获取超时设置，默认为120秒
        self.timeout = self.pipeline_config['ai']['n8n-service-api'].get('timeout', 120)

        # 获取输出键名，默认为response
        self.output_key = self.pipeline_config['ai']['n8n-service-api'].get('output-key', 'response')

        # 获取认证类型，默认为none
        self.auth_type = self.pipeline_config['ai']['n8n-service-api'].get('auth-type', 'none')

        # 根据认证类型获取相应的认证信息
        if self.auth_type == 'basic':
            self.basic_username = self.pipeline_config['ai']['n8n-service-api'].get('basic-username', '')
            self.basic_password = self.pipeline_config['ai']['n8n-service-api'].get('basic-password', '')
        elif self.auth_type == 'jwt':
            self.jwt_secret = self.pipeline_config['ai']['n8n-service-api'].get('jwt-secret', '')
            self.jwt_algorithm = self.pipeline_config['ai']['n8n-service-api'].get('jwt-algorithm', 'HS256')
        elif self.auth_type == 'header':
            self.header_name = self.pipeline_config['ai']['n8n-service-api'].get('header-name', '')
            self.header_value = self.pipeline_config['ai']['n8n-service-api'].get('header-value', '')

    async def _preprocess_user_message(self, query: pipeline_query.Query) -> str:
        """预处理用户消息，提取纯文本

        Returns:
            str: 纯文本消息
        """
        plain_text = ''

        if isinstance(query.user_message.content, list):
            for ce in query.user_message.content:
                if ce.type == 'text':
                    plain_text += ce.text
                # 注意：n8n webhook目前不支持直接处理图片，如需支持可在此扩展
        elif isinstance(query.user_message.content, str):
            plain_text = query.user_message.content

        return plain_text

    async def _process_response(
        self, response: aiohttp.ClientResponse
    ) -> typing.AsyncGenerator[provider_message.Message, None]:
        """处理响应——支持流式格式和普通 JSON 格式"""
        full_content = ''
        full_text = ''
        chunk_idx = 0
        is_final = False
        message_idx = 0

        buffer = ''
        decoder = json.JSONDecoder()

        async for raw_chunk in response.content.iter_chunked(1024):
            if not raw_chunk:
                continue

            try:
                # 将 bytes 解码为字符串（容忍错误）
                if isinstance(raw_chunk, (bytes, bytearray)):
                    chunk_str = raw_chunk.decode('utf-8', errors='replace')
                else:
                    chunk_str = str(raw_chunk)

                full_text += chunk_str
                buffer += chunk_str

                # 尝试从 buffer 中循环解析出 JSON 对象（处理多个对象或部分对象）
                while buffer:
                    buffer = buffer.lstrip()
                    if not buffer:
                        break
                    try:
                        obj, idx = decoder.raw_decode(buffer)
                        buffer = buffer[idx:]

                        if not isinstance(obj, dict):
                            # 忽略非字典类型的顶级 JSON
                            continue

                        if obj.get('type') == 'item' and 'content' in obj:
                            chunk_idx += 1
                            content = obj['content']
                            full_content += content
                        elif obj.get('type') == 'end':
                            is_final = True

                        if is_final or (chunk_idx > 0 and chunk_idx % 8 == 0):
                            message_idx += 1
                            yield provider_message.MessageChunk(
                                role='assistant',
                                content=full_content,
                                is_final=is_final,
                                msg_sequence=message_idx,
                            )
                    except json.JSONDecodeError:
                        # buffer 末尾可能是一个不完整的 JSON，等待更多数据
                        break
            except Exception as e:
                # 记录解析失败并继续接收后续 chunk
                try:
                    preview = chunk_str[:200]
                except Exception:
                    preview = '<unavailable>'
                self.ap.logger.warning(f'Failed to process chunk: {e}; chunk preview: {preview}')

        # 流结束后，尝试解析残余 buffer
        if buffer:
            try:
                buffer = buffer.strip()
                if buffer:
                    obj, _ = decoder.raw_decode(buffer)
                    if isinstance(obj, dict):
                        if obj.get('type') == 'item' and 'content' in obj:
                            chunk_idx += 1
                            full_content += obj['content']
                        elif obj.get('type') == 'end':
                            is_final = True
                    message_idx += 1
                    yield provider_message.MessageChunk(
                        role='assistant',
                        content=full_content,
                        is_final=is_final,
                        msg_sequence=message_idx,
                    )
            except Exception as e:
                preview = buffer[:200]
                self.ap.logger.warning(f'Failed to parse remaining buffer: {e}; buffer preview: {preview}')

        # n8n 返回普通 JSON 格式（无任何流式 type:item 内容）
        if chunk_idx == 0:
            output_content = ''
            try:
                response_data = json.loads(full_text.strip())
                if isinstance(response_data, dict):
                    if self.output_key in response_data:
                        output_content = response_data[self.output_key]
                    else:
                        output_content = json.dumps(response_data, ensure_ascii=False)
                else:
                    output_content = full_text
            except json.JSONDecodeError:
                output_content = full_text
            self.ap.logger.debug(f'n8n webhook response (non-stream): {full_text[:200]}')
            yield provider_message.MessageChunk(
                role='assistant',
                content=output_content,
                is_final=True,
                msg_sequence=message_idx + 1,
            )

    async def _call_webhook(self, query: pipeline_query.Query) -> typing.AsyncGenerator[provider_message.Message, None]:
        """调用n8n webhook"""
        # 生成会话ID（如果不存在）
        if not query.session.using_conversation.uuid:
            query.session.using_conversation.uuid = str(uuid.uuid4())

        # Keep query variables in sync with the generated/new conversation id.
        # query.variables is later merged into payload and would otherwise
        # overwrite the generated conversation_id with the stale preprocessor
        # value (usually None for a new conversation).
        query.variables['conversation_id'] = query.session.using_conversation.uuid

        # 预处理用户消息
        plain_text = await self._preprocess_user_message(query)

        # 准备请求数据
        payload = {
            # 基本消息内容
            'chatInput': plain_text,  # 考虑到之前用户直接用的message model这里添加新键
            'message': plain_text,
            'user_message_text': plain_text,
            'conversation_id': query.session.using_conversation.uuid,
            'session_id': query.variables.get('session_id', ''),
            'user_id': f'{query.session.launcher_type.value}_{query.session.launcher_id}',
            'msg_create_time': query.variables.get('msg_create_time', ''),
        }

        # 添加所有变量到payload
        payload.update(query.variables)

        try:
            is_stream = await query.adapter.is_stream_output_supported()
        except AttributeError:
            is_stream = False

        try:
            # 准备请求头和认证信息
            headers = {}
            auth = None

            # 根据认证类型设置相应的认证信息
            if self.auth_type == 'basic':
                # 使用Basic认证
                auth = aiohttp.BasicAuth(self.basic_username, self.basic_password)
                self.ap.logger.debug(f'using basic auth: {self.basic_username}')
            elif self.auth_type == 'jwt':
                # 使用JWT认证
                import jwt
                import time

                # 创建JWT令牌
                payload_jwt = {
                    'exp': int(time.time()) + 3600,  # 1小时过期
                    'iat': int(time.time()),
                    'sub': 'n8n-webhook',
                }
                token = jwt.encode(payload_jwt, self.jwt_secret, algorithm=self.jwt_algorithm)

                # 添加到Authorization头
                headers['Authorization'] = f'Bearer {token}'
                self.ap.logger.debug('using jwt auth')
            elif self.auth_type == 'header':
                # 使用自定义请求头认证
                headers[self.header_name] = self.header_value
                self.ap.logger.debug(f'using header auth: {self.header_name}')
            else:
                self.ap.logger.debug('no auth')

            # 调用webhook
            session = httpclient.get_session()
            async with session.post(
                self.webhook_url, json=payload, headers=headers, auth=auth, timeout=self.timeout
            ) as response:
                if response.status != 200:
                    error_text = await response.text()
                    self.ap.logger.error(f'n8n webhook call failed: {response.status}, {error_text}')
                    raise Exception(f'n8n webhook call failed: {response.status}, {error_text}')

                async for chunk in self._process_response(response):
                    if is_stream:
                        yield chunk
                    elif chunk.is_final:
                        yield provider_message.Message(
                            role='assistant',
                            content=chunk.content,
                        )
        except Exception as e:
            self.ap.logger.error(f'n8n webhook call exception: {str(e)}')
            raise N8nAPIError(f'n8n webhook call exception: {str(e)}')

    async def run(self, query: pipeline_query.Query) -> typing.AsyncGenerator[provider_message.Message, None]:
        """运行请求"""
        async for msg in self._call_webhook(query):
            yield msg