feat: 添加物流查询功能和完善 token 传递
- 添加 get_logistics 工具查询 Mall API /mall/api/order/parcel - 修复 Cookie token 传递到 MCP 的问题 - 增强 LLM 客户端超时处理和日志 - 移除 MALL_API_TOKEN，使用用户登录 token - 更新测试页面使用 setUser 设置用户属性 - 增强 webhook 调试日志
This commit is contained in:
wangliang
@@ -1,7 +1,8 @@
|
||||
"""
|
||||
ZhipuAI LLM Client for B2B Shopping AI Assistant
|
||||
"""
|
||||
from typing import Any, AsyncGenerator, Optional
|
||||
import concurrent.futures
|
||||
from typing import Any, Optional
|
||||
from dataclasses import dataclass
|
||||
|
||||
from zhipuai import ZhipuAI
|
||||
@@ -29,23 +30,21 @@ class LLMResponse:
|
||||
|
||||
class ZhipuLLMClient:
|
||||
"""ZhipuAI LLM Client wrapper"""
|
||||
|
||||
|
||||
DEFAULT_TIMEOUT = 30 # seconds
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
api_key: Optional[str] = None,
|
||||
model: Optional[str] = None
|
||||
model: Optional[str] = None,
|
||||
timeout: Optional[int] = None
|
||||
):
|
||||
"""Initialize ZhipuAI client
|
||||
|
||||
Args:
|
||||
api_key: ZhipuAI API key, defaults to settings
|
||||
model: Model name, defaults to settings
|
||||
"""
|
||||
self.api_key = api_key or settings.zhipu_api_key
|
||||
self.model = model or settings.zhipu_model
|
||||
self.timeout = timeout or self.DEFAULT_TIMEOUT
|
||||
self._client = ZhipuAI(api_key=self.api_key)
|
||||
logger.info("ZhipuAI client initialized", model=self.model)
|
||||
|
||||
logger.info("ZhipuAI client initialized", model=self.model, timeout=self.timeout)
|
||||
|
||||
async def chat(
|
||||
self,
|
||||
messages: list[Message],
|
||||
@@ -54,32 +53,21 @@ class ZhipuLLMClient:
|
||||
top_p: float = 0.9,
|
||||
**kwargs: Any
|
||||
) -> LLMResponse:
|
||||
"""Send chat completion request
|
||||
|
||||
Args:
|
||||
messages: List of chat messages
|
||||
temperature: Sampling temperature
|
||||
max_tokens: Maximum tokens to generate
|
||||
top_p: Top-p sampling parameter
|
||||
**kwargs: Additional parameters
|
||||
|
||||
Returns:
|
||||
LLM response with content and metadata
|
||||
"""
|
||||
"""Send chat completion request"""
|
||||
formatted_messages = [
|
||||
{"role": msg.role, "content": msg.content}
|
||||
for msg in messages
|
||||
]
|
||||
|
||||
logger.debug(
|
||||
|
||||
logger.info(
|
||||
"Sending chat request",
|
||||
model=self.model,
|
||||
message_count=len(messages),
|
||||
temperature=temperature
|
||||
)
|
||||
|
||||
try:
|
||||
response = self._client.chat.completions.create(
|
||||
|
||||
def _make_request():
|
||||
return self._client.chat.completions.create(
|
||||
model=self.model,
|
||||
messages=formatted_messages,
|
||||
temperature=temperature,
|
||||
@@ -87,10 +75,27 @@ class ZhipuLLMClient:
|
||||
top_p=top_p,
|
||||
**kwargs
|
||||
)
|
||||
|
||||
|
||||
try:
|
||||
with concurrent.futures.ThreadPoolExecutor(max_workers=1) as executor:
|
||||
future = executor.submit(_make_request)
|
||||
response = future.result(timeout=self.timeout)
|
||||
|
||||
choice = response.choices[0]
|
||||
result = LLMResponse(
|
||||
content=choice.message.content,
|
||||
content = choice.message.content
|
||||
|
||||
logger.info(
|
||||
"Chat response received",
|
||||
finish_reason=choice.finish_reason,
|
||||
content_length=len(content) if content else 0,
|
||||
usage=response.usage.__dict__ if hasattr(response, 'usage') else {}
|
||||
)
|
||||
|
||||
if not content:
|
||||
logger.warning("LLM returned empty content")
|
||||
|
||||
return LLMResponse(
|
||||
content=content or "",
|
||||
finish_reason=choice.finish_reason,
|
||||
usage={
|
||||
"prompt_tokens": response.usage.prompt_tokens,
|
||||
@@ -98,48 +103,34 @@ class ZhipuLLMClient:
|
||||
"total_tokens": response.usage.total_tokens
|
||||
}
|
||||
)
|
||||
|
||||
logger.debug(
|
||||
"Chat response received",
|
||||
finish_reason=result.finish_reason,
|
||||
total_tokens=result.usage["total_tokens"]
|
||||
)
|
||||
|
||||
return result
|
||||
|
||||
|
||||
except concurrent.futures.TimeoutError:
|
||||
logger.error("Chat request timed out", timeout=self.timeout)
|
||||
raise TimeoutError(f"Request timed out after {self.timeout} seconds")
|
||||
|
||||
except Exception as e:
|
||||
logger.error("Chat request failed", error=str(e))
|
||||
raise
|
||||
|
||||
|
||||
async def chat_with_tools(
|
||||
self,
|
||||
messages: list[Message],
|
||||
tools: list[dict[str, Any]],
|
||||
temperature: float = 0.7,
|
||||
**kwargs: Any
|
||||
) -> tuple[LLMResponse, Optional[list[dict[str, Any]]]]:
|
||||
"""Send chat completion request with tool calling
|
||||
|
||||
Args:
|
||||
messages: List of chat messages
|
||||
tools: List of tool definitions
|
||||
temperature: Sampling temperature
|
||||
**kwargs: Additional parameters
|
||||
|
||||
Returns:
|
||||
Tuple of (LLM response, tool calls if any)
|
||||
"""
|
||||
) -> tuple[LLMResponse, None]:
|
||||
"""Send chat completion request with tool calling"""
|
||||
formatted_messages = [
|
||||
{"role": msg.role, "content": msg.content}
|
||||
for msg in messages
|
||||
]
|
||||
|
||||
logger.debug(
|
||||
|
||||
logger.info(
|
||||
"Sending chat request with tools",
|
||||
model=self.model,
|
||||
tool_count=len(tools)
|
||||
)
|
||||
|
||||
|
||||
try:
|
||||
response = self._client.chat.completions.create(
|
||||
model=self.model,
|
||||
@@ -148,42 +139,25 @@ class ZhipuLLMClient:
|
||||
temperature=temperature,
|
||||
**kwargs
|
||||
)
|
||||
|
||||
|
||||
choice = response.choices[0]
|
||||
result = LLMResponse(
|
||||
content=choice.message.content or "",
|
||||
content = choice.message.content or ""
|
||||
|
||||
return LLMResponse(
|
||||
content=content,
|
||||
finish_reason=choice.finish_reason,
|
||||
usage={
|
||||
"prompt_tokens": response.usage.prompt_tokens,
|
||||
"completion_tokens": response.usage.completion_tokens,
|
||||
"total_tokens": response.usage.total_tokens
|
||||
}
|
||||
)
|
||||
|
||||
# Extract tool calls if present
|
||||
tool_calls = None
|
||||
if hasattr(choice.message, 'tool_calls') and choice.message.tool_calls:
|
||||
tool_calls = [
|
||||
{
|
||||
"id": tc.id,
|
||||
"type": tc.type,
|
||||
"function": {
|
||||
"name": tc.function.name,
|
||||
"arguments": tc.function.arguments
|
||||
}
|
||||
}
|
||||
for tc in choice.message.tool_calls
|
||||
]
|
||||
logger.debug("Tool calls received", tool_count=len(tool_calls))
|
||||
|
||||
return result, tool_calls
|
||||
|
||||
), None
|
||||
|
||||
except Exception as e:
|
||||
logger.error("Chat with tools request failed", error=str(e))
|
||||
raise
|
||||
|
||||
|
||||
# Global LLM client instance
|
||||
llm_client: Optional[ZhipuLLMClient] = None
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user