[Bug] Invalid Token Error in NextChat+One-API Local Deployment When Using SiliconFlow Model

### 📦 Deployment Method

Docker

### 📌 Version

2.16.0

### 💻 Operating System

Other Linux

### 📌 System Version

1panel Docker

### 🌐 Browser

Chrome

### 📌 Browser Version

Latest

### 🐛 Bug Description

When deploying NextChat with One-API locally, an "Invalid token" error occurs when attempting to use the SiliconFlow model. The issue arises because NextChat does not correctly route requests through One-API's gateway, instead attempting to directly call SiliconFlow's API without using the One-API Token. Other UI applications (e.g., Chatbox) work correctly with the same setup.

### 📷 Recurrence Steps

1. Deploy NextChat and One-API locally.
2. Add SiliconFlow's API key and other channels (e.g., Alibaba's Tongyi Qianwen) in One-API.
3. Configure NextChat's environment variables with the One-API token as follows:
```yaml
environment:
- OPENAI_API_KEY=sk-dUJhlhHAabdVXsqN22B205Bxxxxxxxxxxxxx6e65B1Ad
- CODE=xxxxx
- BASE_URL=http://154.xxx.241.166:3000
- CUSTOM_MODELS=-all,+deepseek-ai/DeepSeek-R1,+Pro/deepseek-ai/DeepSeek-R1,+deepseek-ai/DeepSeek-V3,+Pro/deepseek-ai/DeepSeek-V3,+deepseek-r1,+deepseek-v3,+qwen-max-latest,+deepseek-r1-250120,+deepseek-v3-241226
- DEFAULT_MODEL=deepseek-ai/DeepSeek-V3
```
4. Attempt to use the SiliconFlow model in NextChat.

### 🚦 Expected Behavior

**Expected Behavior:**
NextChat should route requests through One-API's gateway and successfully connect to the SiliconFlow model using the One-API Token.

**Actual Behavior:**
An "Invalid token" error occurs. The logs indicate that NextChat is attempting to directly call SiliconFlow's API without using the One-API Token.

### 📝 Additional Information

**Logs:**
```
1Panel-chatgpt-next-web-Z6DO | [Server Config] using 1 of 1 api key - sk-dUJhlhHAabdVXsqN22B2eeeeeeeeeeeaAd1e55B46e65B1Ad
1Panel-chatgpt-next-web-Z6DO | [siliconflow Route] params { provider: 'siliconflow', path: [ 'v1', 'chat', 'completions' ] }
1Panel-chatgpt-next-web-Z6DO | [SiliconFlow Route] params { provider: 'siliconflow', path: [ 'v1', 'chat', 'completions' ] }
1Panel-chatgpt-next-web-Z6DO | [Server Config] using 1 of 1 api key - sk-dUJhlhHAabdVXsqN22B2eeeeeeeeeeeaAd1e55B46e65B1Ad
1Panel-chatgpt-next-web-Z6DO | [Auth] allowed hashed codes: [ '4f7487bda8deeeeeeeeeee7e3633ff38a7d' ]
1Panel-chatgpt-next-web-Z6DO | [Auth] got access code: xxxxxxxx
1Panel-chatgpt-next-web-Z6DO | [Auth] hashed access code: 4f7487bda8deeeeeeeeeee7e3633ff38a7d
1Panel-chatgpt-next-web-Z6DO | [User IP] 172.70.**.68
1Panel-chatgpt-next-web-Z6DO | [Time] 2/23/2025, 1:04:23 PM
1Panel-chatgpt-next-web-Z6DO | [Server Config] using 1 of 1 api key - sk-dUJhlhHAabdVXsqN22B2eeeeeeeeeeeaAd1e55B46e65B1Ad
1Panel-chatgpt-next-web-Z6DO | [Auth] admin did not provide an api key
1Panel-chatgpt-next-web-Z6DO | [Proxy] /v1/chat/completions
1Panel-chatgpt-next-web-Z6DO | [Base Url] https://api.siliconflow.cn
1Panel-chatgpt-next-web-Z6DO | [Server Config] using 1 of 1 api key - sk-dUJhlhHAabdVXsqN22B2eeeeeeeeeeeaAd1e55B46e65B1Ad
```

**Root Cause:**
NextChat does not correctly route requests through One-API's gateway, instead attempting to directly call SiliconFlow's API without using the One-API Token.

**Proposed Solution:**
1.Verify that BASE_URL in NextChat's configuration correctly points to One-API's address.
2.Ensure that NextChat's code logic routes all requests through One-API's gateway.
3.Add detailed logging to debug the request routing process.

**Additional Information:**
-Other UI applications (e.g., Chatbox) work correctly with the same setup.
-The issue is specific to NextChat when using the SiliconFlow model.

---

Let me know if you need further adjustments!