update: 前端模型显示名称同步升级 - GLM-4.7-Flash -> GLM-5.1, DeepSeek-Reasoner -> DeepSeek-V4-Pro
All checks were successful
构建并部署 AI Agent 服务 / deploy (push) Successful in 6m12s

This commit is contained in:
2026-05-01 03:08:24 +08:00
parent c4c86a5476
commit c90471d67d
3 changed files with 7 additions and 7 deletions

View File

@@ -85,8 +85,8 @@ graph TB
AgentService -->|模型路由| ChatServices[模型服务层 chat_services]
ChatServices -->|自动降级| FallbackChain[FallbackServiceChain]
FallbackChain -->|创建| Zhipu[智谱 GLM-4.7]
FallbackChain -->|创建| DeepSeek[DeepSeek Reasoner]
FallbackChain -->|创建| Zhipu[智谱 GLM-5.1]
FallbackChain -->|创建| DeepSeek[DeepSeek V4-Pro]
FallbackChain -->|创建| LocalGemma[本地 Gemma-4]
AgentService -->|初始化| LangGraph[LangGraph 工作流引擎]
@@ -1560,8 +1560,8 @@ streamlit run frontend/src/frontend_main.py
### 多模型切换
1. 在左侧边栏选择模型:
- **智谱 GLM-4.7**:在线服务,速度快
- **DeepSeek Reasoner**:深度推理模型
- **智谱 GLM-5.1**:在线服务,速度快
- **DeepSeek V4-Pro**:深度推理模型
- **本地 Gemma-4**:本地部署,隐私性好
2. 可随时切换,甚至在同一会话中

View File

@@ -156,7 +156,7 @@ def _handle_ai_response():
display_text = raw_text
is_thinking = False
# 1. 原生 API 推理模式 (如 DeepSeek-Reasoner)
# 1. 原生 API 推理模式 (如 DeepSeek-V4-Pro)
if api_thought:
is_thinking = not bool(raw_text.strip())

View File

@@ -72,9 +72,9 @@ class FrontendConfig:
"""初始化后处理 - 设置默认值和加载环境变量"""
if self.model_options is None:
self.model_options = {
"zhipu": "智谱 GLM-4.7-Flash(在线)",
"zhipu": "智谱 GLM-5.1(在线)",
"local": "本地 llama.cppGemma-4",
"deepseek": "DeepSeek V3.2(在线)"
"deepseek": "DeepSeek V4-Pro(在线)"
}
# 从环境变量加载配置(优先级最高)