Merge branch 'master' into version/4.0

pkg/provider/modelmgr/requesters/anthropicmsgs.py

@@ -2,7 +2,8 @@ from __future__ import annotations
 
 import typing
 import json
-
+import platform
+import socket
 import anthropic
 import httpx
 
@@ -25,6 +26,12 @@ class AnthropicMessages(requester.LLMAPIRequester):
     }
 
     async def initialize(self):
+        # 兼容 Windows 缺失 TCP_KEEPINTVL 和 TCP_KEEPCNT 的问题
+        if platform.system() == 'Windows':
+            if not hasattr(socket, 'TCP_KEEPINTVL'):
+                socket.TCP_KEEPINTVL = 0
+            if not hasattr(socket, 'TCP_KEEPCNT'):
+                socket.TCP_KEEPCNT = 0
         httpx_client = anthropic._base_client.AsyncHttpxClientWrapper(
             base_url=self.requester_cfg['base_url'],
             # cast to a valid type because mypy doesn't understand our type narrowing
@@ -61,9 +68,11 @@ class AnthropicMessages(requester.LLMAPIRequester):
             if m.role == 'system':
                 system_role_message = m
 
-                messages.pop(i)
                 break
 
+        if system_role_message:
+            messages.pop(i)
+
         if isinstance(system_role_message, llm_entities.Message) and isinstance(
             system_role_message.content, str
         ):

pkg/provider/modelmgr/requesters/bailianchatcmpl.py

@@ -3,10 +3,10 @@ from __future__ import annotations
 import typing
 import openai
 
-from . import chatcmpl
+from . import modelscopechatcmpl
 
 
-class BailianChatCompletions(chatcmpl.OpenAIChatCompletions):
+class BailianChatCompletions(modelscopechatcmpl.ModelScopeChatCompletions):
     """阿里云百炼大模型平台 ChatCompletion API 请求器"""
 
     client: openai.AsyncClient

pkg/provider/modelmgr/requesters/chatcmpl.py

@@ -26,7 +26,7 @@ class OpenAIChatCompletions(requester.LLMAPIRequester):
     async def initialize(self):
         self.client = openai.AsyncClient(
             api_key='',
-            base_url=self.requester_cfg['base_url'],
+            base_url=self.requester_cfg['base-url'].replace(' ', ''),
             timeout=self.requester_cfg['timeout'],
             http_client=httpx.AsyncClient(
                 trust_env=True, timeout=self.requester_cfg['timeout']
@@ -36,8 +36,9 @@ class OpenAIChatCompletions(requester.LLMAPIRequester):
     async def _req(
         self,
         args: dict,
+        extra_body: dict = {},
     ) -> chat_completion.ChatCompletion:
-        return await self.client.chat.completions.create(**args)
+        return await self.client.chat.completions.create(**args, extra_body=extra_body)
 
     async def _make_msg(
         self,
@@ -49,6 +50,21 @@ class OpenAIChatCompletions(requester.LLMAPIRequester):
         if 'role' not in chatcmpl_message or chatcmpl_message['role'] is None:
             chatcmpl_message['role'] = 'assistant'
 
+        reasoning_content = (
+            chatcmpl_message['reasoning_content']
+            if 'reasoning_content' in chatcmpl_message
+            else None
+        )
+
+        # deepseek的reasoner模型
+        if reasoning_content is not None:
+            chatcmpl_message['content'] = (
+                '<think>\n'
+                + reasoning_content
+                + '\n</think>\n'
+                + chatcmpl_message['content']
+            )
+
         message = llm_entities.Message(**chatcmpl_message)
 
         return message
@@ -87,7 +103,7 @@ class OpenAIChatCompletions(requester.LLMAPIRequester):
         args['messages'] = messages
 
         # 发送请求
-        resp = await self._req(args)
+        resp = await self._req(args, extra_body=self.requester_cfg['args'])
 
         # 处理请求结果
         message = await self._make_msg(resp)

pkg/provider/modelmgr/requesters/deepseekchatcmpl.py

@@ -47,7 +47,7 @@ class DeepseekChatCompletions(chatcmpl.OpenAIChatCompletions):
         args['messages'] = messages
 
         # 发送请求
-        resp = await self._req(args)
+        resp = await self._req(args, extra_body=self.requester_cfg['args'])
 
         if resp is None:
             raise errors.RequesterError('接口返回为空，请确定模型提供商服务是否正常')

pkg/provider/modelmgr/requesters/giteeaichatcmpl.py

@@ -44,7 +44,7 @@ class GiteeAIChatCompletions(chatcmpl.OpenAIChatCompletions):
 
         args['messages'] = req_messages
 
-        resp = await self._req(args)
+        resp = await self._req(args, extra_body=self.requester_cfg['args'])
 
         message = await self._make_msg(resp)
 

pkg/provider/modelmgr/requesters/modelscopechatcmpl.py

@@ -0,0 +1,207 @@
+from __future__ import annotations
+ 
+import asyncio
+import typing
+import json
+import base64
+from typing import AsyncGenerator
+
+import openai
+import openai.types.chat.chat_completion as chat_completion
+import openai.types.chat.chat_completion_message_tool_call as chat_completion_message_tool_call
+import httpx
+import aiohttp
+import async_lru
+
+from .. import entities, errors, requester
+from ....core import entities as core_entities, app
+from ... import entities as llm_entities
+from ...tools import entities as tools_entities
+from ....utils import image
+
+
+class ModelScopeChatCompletions(requester.LLMAPIRequester):
+    """ModelScope ChatCompletion API 请求器"""
+
+    client: openai.AsyncClient
+
+    requester_cfg: dict
+
+    def __init__(self, ap: app.Application):
+        self.ap = ap
+
+        self.requester_cfg = self.ap.provider_cfg.data['requester']['modelscope-chat-completions']
+
+    async def initialize(self):
+
+        self.client = openai.AsyncClient(
+            api_key="",
+            base_url=self.requester_cfg['base-url'],
+            timeout=self.requester_cfg['timeout'],
+            http_client=httpx.AsyncClient(
+                trust_env=True,
+                timeout=self.requester_cfg['timeout']
+            )
+        )
+
+    async def _req(
+        self,
+        args: dict,
+    ) -> chat_completion.ChatCompletion:
+        args["stream"] = True
+
+        chunk = None
+
+        pending_content = ""
+
+        tool_calls = []
+
+        resp_gen: openai.AsyncStream = await self.client.chat.completions.create(**args)
+
+        async for chunk in resp_gen:
+            # print(chunk)
+            if not chunk or not chunk.id or not chunk.choices or not chunk.choices[0] or not chunk.choices[0].delta:
+                continue
+
+            if chunk.choices[0].delta.content is not None:
+                pending_content += chunk.choices[0].delta.content
+
+            if chunk.choices[0].delta.tool_calls is not None:
+                for tool_call in chunk.choices[0].delta.tool_calls:
+                    for tc in tool_calls:
+                        if tc.index == tool_call.index:
+                            tc.function.arguments += tool_call.function.arguments
+                            break
+                    else:
+                        tool_calls.append(tool_call)
+            
+            if chunk.choices[0].finish_reason is not None:
+                break
+
+        real_tool_calls = []
+
+        for tc in tool_calls:
+            function = chat_completion_message_tool_call.Function(
+                name=tc.function.name,
+                arguments=tc.function.arguments
+            )
+            real_tool_calls.append(chat_completion_message_tool_call.ChatCompletionMessageToolCall(
+                id=tc.id,
+                function=function,
+                type="function"
+            ))
+
+        return chat_completion.ChatCompletion(
+            id=chunk.id,
+            object="chat.completion",
+            created=chunk.created,
+            choices=[
+                chat_completion.Choice(
+                    index=0,
+                    message=chat_completion.ChatCompletionMessage(
+                        role="assistant",
+                        content=pending_content,
+                        tool_calls=real_tool_calls if len(real_tool_calls) > 0 else None
+                    ),
+                    finish_reason=chunk.choices[0].finish_reason if hasattr(chunk.choices[0], 'finish_reason') and chunk.choices[0].finish_reason is not None else 'stop',
+                    logprobs=chunk.choices[0].logprobs,
+                )
+            ],
+            model=chunk.model,
+            service_tier=chunk.service_tier if hasattr(chunk, 'service_tier') else None,
+            system_fingerprint=chunk.system_fingerprint if hasattr(chunk, 'system_fingerprint') else None,
+            usage=chunk.usage if hasattr(chunk, 'usage') else None
+        ) if chunk else None
+        return await self.client.chat.completions.create(**args)
+
+    async def _make_msg(
+        self,
+        chat_completion: chat_completion.ChatCompletion,
+    ) -> llm_entities.Message:
+        chatcmpl_message = chat_completion.choices[0].message.dict()
+
+        # 确保 role 字段存在且不为 None
+        if 'role' not in chatcmpl_message or chatcmpl_message['role'] is None:
+            chatcmpl_message['role'] = 'assistant'
+
+        message = llm_entities.Message(**chatcmpl_message)
+
+        return message
+
+    async def _closure(
+        self,
+        query: core_entities.Query,
+        req_messages: list[dict],
+        use_model: entities.LLMModelInfo,
+        use_funcs: list[tools_entities.LLMFunction] = None,
+    ) -> llm_entities.Message:
+        self.client.api_key = use_model.token_mgr.get_token()
+
+        args = self.requester_cfg['args'].copy()
+        args["model"] = use_model.name if use_model.model_name is None else use_model.model_name
+
+        if use_funcs:
+            tools = await self.ap.tool_mgr.generate_tools_for_openai(use_funcs)
+
+            if tools:
+                args["tools"] = tools
+
+        # 设置此次请求中的messages
+        messages = req_messages.copy()
+
+        # 检查vision
+        for msg in messages:
+            if 'content' in msg and isinstance(msg["content"], list):
+                for me in msg["content"]:
+                    if me["type"] == "image_base64":
+                        me["image_url"] = {
+                            "url": me["image_base64"]
+                        }
+                        me["type"] = "image_url"
+                        del me["image_base64"]
+
+        args["messages"] = messages
+
+        # 发送请求
+        resp = await self._req(args)
+
+        # 处理请求结果
+        message = await self._make_msg(resp)
+
+        return message
+
+    async def call(
+        self,
+        query: core_entities.Query,
+        model: entities.LLMModelInfo,
+        messages: typing.List[llm_entities.Message],
+        funcs: typing.List[tools_entities.LLMFunction] = None,
+    ) -> llm_entities.Message:
+        req_messages = []  # req_messages 仅用于类内，外部同步由 query.messages 进行
+        for m in messages:
+            msg_dict = m.dict(exclude_none=True)
+            content = msg_dict.get("content")
+            if isinstance(content, list):
+                # 检查 content 列表中是否每个部分都是文本
+                if all(isinstance(part, dict) and part.get("type") == "text" for part in content):
+                    # 将所有文本部分合并为一个字符串
+                    msg_dict["content"] = "\n".join(part["text"] for part in content)
+            req_messages.append(msg_dict)
+
+        try:
+            return await self._closure(query=query, req_messages=req_messages, use_model=model, use_funcs=funcs)
+        except asyncio.TimeoutError:
+            raise errors.RequesterError('请求超时')
+        except openai.BadRequestError as e:
+            if 'context_length_exceeded' in e.message:
+                raise errors.RequesterError(f'上文过长，请重置会话: {e.message}')
+            else:
+                raise errors.RequesterError(f'请求参数错误: {e.message}')
+        except openai.AuthenticationError as e:
+            raise errors.RequesterError(f'无效的 api-key: {e.message}')
+        except openai.NotFoundError as e:
+            raise errors.RequesterError(f'请求路径错误: {e.message}')
+        except openai.RateLimitError as e:
+            raise errors.RequesterError(f'请求过于频繁或余额不足: {e.message}')
+        except openai.APIError as e:
+            raise errors.RequesterError(f'请求错误: {e.message}')

pkg/provider/modelmgr/requesters/modelscopechatcmpl.yaml

@@ -0,0 +1,34 @@
+apiVersion: v1
+kind: LLMAPIRequester
+metadata:
+  name: modelscope-chat-completions
+  label:
+    en_US: ModelScope
+    zh_CN: 魔搭社区
+spec:
+  config:
+    - name: base-url
+      label:
+        en_US: Base URL
+        zh_CN: 基础 URL
+      type: string
+      required: true
+      default: "https://api-inference.modelscope.cn/v1"
+    - name: args
+      label:
+        en_US: Args
+        zh_CN: 附加参数
+      type: object
+      required: true
+      default: {}
+    - name: timeout
+      label:
+        en_US: Timeout
+        zh_CN: 超时时间
+      type: int
+      required: true
+      default: 120
+execution:
+  python:
+    path: ./modelscopechatcmpl.py
+    attr: ModelScopeChatCompletions

pkg/provider/modelmgr/requesters/moonshotchatcmpl.py

@@ -45,13 +45,13 @@ class MoonshotChatCompletions(chatcmpl.OpenAIChatCompletions):
             if 'content' in m and isinstance(m['content'], list):
                 m['content'] = ' '.join([c['text'] for c in m['content']])
 
-        # 删除空的
-        messages = [m for m in messages if m['content'].strip() != '']
+        # 删除空的，不知道干嘛的，直接删了。
+        # messages = [m for m in messages if m["content"].strip() != "" and ('tool_calls' not in m or not m['tool_calls'])]
 
         args['messages'] = messages
 
         # 发送请求
-        resp = await self._req(args)
+        resp = await self._req(args, extra_body=self.requester_cfg['args'])
 
         # 处理请求结果
         message = await self._make_msg(resp)

pkg/provider/modelmgr/requesters/ppiochatcmpl.py

@@ -0,0 +1,20 @@
+
+from __future__ import annotations
+
+import openai
+
+from . import chatcmpl, modelscopechatcmpl
+from .. import requester
+from ....core import app
+
+class PPIOChatCompletions(chatcmpl.OpenAIChatCompletions):
+    """欧派云 ChatCompletion API 请求器"""
+
+    client: openai.AsyncClient
+
+    requester_cfg: dict
+
+    def __init__(self, ap: app.Application):
+        self.ap = ap
+
+        self.requester_cfg = self.ap.provider_cfg.data['requester']['ppio-chat-completions']

pkg/provider/modelmgr/requesters/ppiochatcmpl.yaml

@@ -0,0 +1,34 @@
+apiVersion: v1
+kind: LLMAPIRequester
+metadata:
+  name: ppio-chat-completions
+  label:
+    en_US: ppio 
+    zh_CN: 派欧云
+spec:
+  config:
+    - name: base-url
+      label:
+        en_US: Base URL
+        zh_CN: 基础 URL
+      type: string
+      required: true
+      default: "https://api.ppinfra.com/v3/openai"
+    - name: args
+      label:
+        en_US: Args
+        zh_CN: 附加参数
+      type: object
+      required: true
+      default: {}
+    - name: timeout
+      label:
+        en_US: Timeout
+        zh_CN: 超时时间
+      type: int
+      required: true
+      default: 120
+execution:
+  python:
+    path: ./ppiochatcmpl.py
+    attr: PPIOChatCompletions