chore: 更新版本号至2.1.8

- 新增CLOUDFLARE_IMGBED_UPLOAD_FOLDER环境变量配置
- 用户可通过该配置项指定图片在CloudFlare图床中的上传路径

.env.example

@@ -33,6 +33,8 @@ TIME_OUT=300
 # 代理服务器配置 (支持 http 和 socks5)
 # 示例: PROXIES=["http://user:pass@host:port", "socks5://host:port"]
 PROXIES=[]
+# 对同一个API_KEY使用代理列表中固定的IP策略
+PROXIES_USE_CONSISTENCY_HASH_BY_API_KEY=true
 #########################image_generate 相关配置###########################
 PAID_KEY=AIzaSyxxxxxxxxxxxxxxxxxxx
 CREATE_IMAGE_MODEL=imagen-3.0-generate-002
@@ -41,6 +43,7 @@ SMMS_SECRET_TOKEN=XXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
 PICGO_API_KEY=xxxx
 CLOUDFLARE_IMGBED_URL=https://xxxxxxx.pages.dev/upload
 CLOUDFLARE_IMGBED_AUTH_CODE=xxxxxxxxx
+CLOUDFLARE_IMGBED_UPLOAD_FOLDER=
 ##########################################################################
 #########################stream_optimizer 相关配置########################
 STREAM_OPTIMIZER_ENABLED=false
@@ -72,3 +75,8 @@ FAKE_STREAM_EMPTY_DATA_INTERVAL_SECONDS=5
 # 安全设置 (JSON 字符串格式)
 # 注意：这里的示例值可能需要根据实际模型支持情况调整
 SAFETY_SETTINGS=[{"category": "HARM_CATEGORY_HARASSMENT", "threshold": "OFF"}, {"category": "HARM_CATEGORY_HATE_SPEECH", "threshold": "OFF"}, {"category": "HARM_CATEGORY_SEXUALLY_EXPLICIT", "threshold": "OFF"}, {"category": "HARM_CATEGORY_DANGEROUS_CONTENT", "threshold": "OFF"}, {"category": "HARM_CATEGORY_CIVIC_INTEGRITY", "threshold": "BLOCK_NONE"}]
+URL_NORMALIZATION_ENABLED=false
+# tts配置
+TTS_MODEL=gemini-2.5-flash-preview-tts
+TTS_VOICE_NAME=Zephyr
+TTS_SPEED=normal

Dockerfile

@@ -14,6 +14,8 @@ ENV BASE_URL=https://generativelanguage.googleapis.com/v1beta
 ENV TOOLS_CODE_EXECUTION_ENABLED=false
 ENV IMAGE_MODELS='["gemini-2.0-flash-exp"]'
 ENV SEARCH_MODELS='["gemini-2.0-flash-exp","gemini-2.0-pro-exp"]'
+ENV URL_NORMALIZATION_ENABLED=false
+ENV CLOUDFLARE_IMGBED_UPLOAD_FOLDER=""
 
 # Expose port
 EXPOSE 8000

README.md

@@ -2,6 +2,12 @@
 
 # Gemini Balance - Gemini API Proxy and Load Balancer
 
+<p align="center">
+  <a href="https://trendshift.io/repositories/13692" target="_blank">
+    <img src="https://trendshift.io/api/badge/repositories/13692" alt="snailyp%2Fgemini-balance | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/>
+  </a>
+</p>
+
 > ⚠️ This project is licensed under the CC BY-NC 4.0 (Attribution-NonCommercial) license. Any form of commercial resale service is prohibited. See the LICENSE file for details.
 
 > I have never sold this service on any platform. If you encounter someone selling this service, they are definitely a reseller. Please be careful not to be deceived.
@@ -11,7 +17,7 @@
 [![Uvicorn](https://img.shields.io/badge/Uvicorn-running-purple.svg)](https://www.uvicorn.org/)
 [![Telegram Group](https://img.shields.io/badge/Telegram-Group-blue.svg?logo=telegram)](https://t.me/+soaHax5lyI0wZDVl)
 
-> Telegram Group: https://t.me/+soaHax5lyI0wZDVl
+> Telegram Group: <https://t.me/+soaHax5lyI0wZDVl>
 
 ## Project Introduction
 
@@ -40,39 +46,39 @@ app/
 
 ## ✨ Feature Highlights
 
-*   **Multi-Key Load Balancing**: Supports configuring multiple Gemini API Keys (`API_KEYS`) for automatic sequential polling, improving availability and concurrency.
+* **Multi-Key Load Balancing**: Supports configuring multiple Gemini API Keys (`API_KEYS`) for automatic sequential polling, improving availability and concurrency.
-*   **Visual Configuration Takes Effect Immediately**: Configurations modified through the admin backend take effect without restarting the service. Remember to click save for changes to apply.
+* **Visual Configuration Takes Effect Immediately**: Configurations modified through the admin backend take effect without restarting the service. Remember to click save for changes to apply.
     ![Configuration Panel](files/image4.png)
-*   **Dual Protocol API Compatibility**: Supports forwarding CHAT API requests in both Gemini and OpenAI formats.
+* **Dual Protocol API Compatibility**: Supports forwarding CHAT API requests in both Gemini and OpenAI formats.
 
     ```plaintext
     openai baseurl `http://localhost:8000(/hf)/v1`
     gemini baseurl `http://localhost:8000(/gemini)/v1beta`
     ```
 
-*   **Supports Image-Text Chat and Image Modification**: `IMAGE_MODELS` configures which models can perform image-text chat and image editing. When actually calling, use the `configured_model-image` model name to use this feature.
+* **Supports Image-Text Chat and Image Modification**: `IMAGE_MODELS` configures which models can perform image-text chat and image editing. When actually calling, use the `configured_model-image` model name to use this feature.
     ![Chat with Image Generation](files/image6.png)
     ![Modify Image](files/image7.png)
-*   **Supports Web Search**: Supports web search. `SEARCH_MODELS` configures which models can perform web searches. When actually calling, use the `configured_model-search` model name to use this feature.
+* **Supports Web Search**: Supports web search. `SEARCH_MODELS` configures which models can perform web searches. When actually calling, use the `configured_model-search` model name to use this feature.
     ![Web Search](files/image8.png)
-*   **Key Status Monitoring**: Provides a `/keys_status` page (requires authentication) to view the status and usage of each Key in real-time.
+* **Key Status Monitoring**: Provides a `/keys_status` page (requires authentication) to view the status and usage of each Key in real-time.
     ![Monitoring Panel](files/image.png)
-*   **Detailed Logging**: Provides detailed error logs for easy troubleshooting.
+* **Detailed Logging**: Provides detailed error logs for easy troubleshooting.
     ![Call Details](files/image1.png)
     ![Log List](files/image2.png)
     ![Log Details](files/image3.png)
-*   **Support for Custom Gemini Proxy**: Supports custom Gemini proxies, such as those built on Deno or Cloudflare.
+* **Support for Custom Gemini Proxy**: Supports custom Gemini proxies, such as those built on Deno or Cloudflare.
-*   **OpenAI Image Generation API Compatibility**: Adapts the `imagen-3.0-generate-002` model interface to be compatible with the OpenAI image generation API, supporting client calls.
+* **OpenAI Image Generation API Compatibility**: Adapts the `imagen-3.0-generate-002` model interface to be compatible with the OpenAI image generation API, supporting client calls.
-*   **Flexible Key Addition**: Flexible way to add keys using regex matching for `gemini_key`, with key deduplication.
+* **Flexible Key Addition**: Flexible way to add keys using regex matching for `gemini_key`, with key deduplication.
     ![Add Key](files/image5.png)
-*   **OpenAI Format Embeddings API Compatibility**: Perfectly adapts to the OpenAI format `embeddings` interface, usable for local document vectorization.
+* **OpenAI Format Embeddings API Compatibility**: Perfectly adapts to the OpenAI format `embeddings` interface, usable for local document vectorization.
-*   **Streamlined Response Optimization**: Optional stream output optimizer (`STREAM_OPTIMIZER_ENABLED`) to improve the experience of long-text stream responses.
+* **Streamlined Response Optimization**: Optional stream output optimizer (`STREAM_OPTIMIZER_ENABLED`) to improve the experience of long-text stream responses.
-*   **Failure Retry and Key Management**: Automatically handles API request failures, retries (`MAX_RETRIES`), automatically disables Keys after too many failures (`MAX_FAILURES`), and periodically checks for recovery (`CHECK_INTERVAL_HOURS`).
+* **Failure Retry and Key Management**: Automatically handles API request failures, retries (`MAX_RETRIES`), automatically disables Keys after too many failures (`MAX_FAILURES`), and periodically checks for recovery (`CHECK_INTERVAL_HOURS`).
-*   **Docker Support**: Supports AMD and ARM architecture Docker deployments. You can also build your own Docker image.
+* **Docker Support**: Supports AMD and ARM architecture Docker deployments. You can also build your own Docker image.
     > Image address: docker pull ghcr.io/snailyp/gemini-balance:latest
-*   **Automatic Model List Maintenance**: Supports fetching OpenAI and Gemini model lists, perfectly compatible with NewAPI's automatic model list fetching, no manual entry required.
+* **Automatic Model List Maintenance**: Supports fetching OpenAI and Gemini model lists, perfectly compatible with NewAPI's automatic model list fetching, no manual entry required.
-*   **Support for Removing Unused Models**: Too many default models are provided, many of which are not used. You can filter them out using `FILTERED_MODELS`.
+* **Support for Removing Unused Models**: Too many default models are provided, many of which are not used. You can filter them out using `FILTERED_MODELS`.
-*   **Proxy Support**: Supports configuring HTTP/SOCKS5 proxy servers (`PROXIES`) for accessing the Gemini API, convenient for use in special network environments. Supports batch adding proxies.
+* **Proxy Support**: Supports configuring HTTP/SOCKS5 proxy servers (`PROXIES`) for accessing the Gemini API, convenient for use in special network environments. Supports batch adding proxies.
 
 ## 🚀 Quick Start
 
@@ -80,79 +86,83 @@ app/
 
 #### a) Build with Dockerfile
 
-1.  **Build Image**:
+1. **Build Image**:
 
     ```bash
     docker build -t gemini-balance .
     ```
 
-2.  **Run Container**:
+2. **Run Container**:
 
     ```bash
     docker run -d -p 8000:8000 --env-file .env gemini-balance
     ```
 
-    *   `-d`: Run in detached mode.
+    * `-d`: Run in detached mode.
-    *   `-p 8000:8000`: Map port 8000 of the container to port 8000 of the host.
+    * `-p 8000:8000`: Map port 8000 of the container to port 8000 of the host.
-    *   `--env-file .env`: Use the `.env` file to set environment variables.
+    * `--env-file .env`: Use the `.env` file to set environment variables.
 
-    > Note: If using an SQLite database, you need to mount a data volume to persist 
+    > Note: If using an SQLite database, you need to mount a data volume to persist
+>
     > ```bash
     > docker run -d -p 8000:8000 --env-file .env -v /path/to/data:/app/data gemini-balance
     > ```
+>
     > Where `/path/to/data` is the data storage path on the host, and `/app/data` is the data directory inside the container.
 
 #### b) Deploy with an Existing Docker Image
 
-1.  **Pull Image**:
+1. **Pull Image**:
 
     ```bash
     docker pull ghcr.io/snailyp/gemini-balance:latest
     ```
 
-2.  **Run Container**:
+2. **Run Container**:
 
     ```bash
     docker run -d -p 8000:8000 --env-file .env ghcr.io/snailyp/gemini-balance:latest
     ```
 
-    *   `-d`: Run in detached mode.
+    * `-d`: Run in detached mode.
-    *   `-p 8000:8000`: Map port 8000 of the container to port 8000 of the host (adjust as needed).
+    * `-p 8000:8000`: Map port 8000 of the container to port 8000 of the host (adjust as needed).
-    *   `--env-file .env`: Use the `.env` file to set environment variables (ensure the `.env` file exists in the directory where the command is executed).
+    * `--env-file .env`: Use the `.env` file to set environment variables (ensure the `.env` file exists in the directory where the command is executed).
 
-    > Note: If using an SQLite database, you need to mount a data volume to persist 
+    > Note: If using an SQLite database, you need to mount a data volume to persist
+>
     > ```bash
     > docker run -d -p 8000:8000 --env-file .env -v /path/to/data:/app/data ghcr.io/snailyp/gemini-balance:latest
     > ```
+>
     > Where `/path/to/data` is the data storage path on the host, and `/app/data` is the data directory inside the container.
 
 ### Run Locally (Suitable for Development and Testing)
 
 If you want to run the source code directly locally for development or testing, follow these steps:
 
-1.  **Ensure Prerequisites are Met**:
+1. **Ensure Prerequisites are Met**:
-    *   Clone the repository locally.
+    * Clone the repository locally.
-    *   Install Python 3.9 or higher.
+    * Install Python 3.9 or higher.
-    *   Create and configure the `.env` file in the project root directory (refer to the "Configure Environment Variables" section above).
+    * Create and configure the `.env` file in the project root directory (refer to the "Configure Environment Variables" section above).
-    *   Install project dependencies:
+    * Install project dependencies:
 
         ```bash
         pip install -r requirements.txt
         ```
 
-2.  **Start Application**:
+2. **Start Application**:
     Run the following command in the project root directory:
 
     ```bash
     uvicorn app.main:app --host 0.0.0.0 --port 8000 --reload
     ```
 
-    *   `app.main:app`: Specifies the location of the FastAPI application instance (the `app` object in the `main.py` file within the `app` module).
+    * `app.main:app`: Specifies the location of the FastAPI application instance (the `app` object in the `main.py` file within the `app` module).
-    *   `--host 0.0.0.0`: Makes the application accessible from any IP address on the local network.
+    * `--host 0.0.0.0`: Makes the application accessible from any IP address on the local network.
-    *   `--port 8000`: Specifies the port number the application listens on (you can change this as needed).
+    * `--port 8000`: Specifies the port number the application listens on (you can change this as needed).
-    *   `--reload`: Enables automatic reloading. When you modify the code, the service will automatically restart, which is very suitable for development environments (remove this option in production environments).
+    * `--reload`: Enables automatic reloading. When you modify the code, the service will automatically restart, which is very suitable for development environments (remove this option in production environments).
 
-3.  **Access Application**:
+3. **Access Application**:
     After the application starts, you can access `http://localhost:8000` (or the host and port you specified) through a browser or API tool.
 
 ### Complete Configuration List
@@ -181,6 +191,7 @@ If you want to run the source code directly locally for development or testing,
 | `SHOW_THINKING_PROCESS`        | Optional, whether to display the model's thinking process                   | `true`                                                                                                                                                                                                                                   |
 | `THINKING_MODELS`              | Optional, list of models that support thinking functions                    | `[]`                                                                                                                                                                                                                                     |
 | `THINKING_BUDGET_MAP`          | Optional, thinking function budget mapping (model_name:budget_value)        | `{}`                                                                                                                                                                                                                                     |
+| `URL_NORMALIZATION_ENABLED`    | Optional, whether to enable intelligent URL routing mapping                 | `false`                                                                                                                                                                                                                                  |
 | `BASE_URL`                     | Optional, Gemini API base URL, no modification needed by default            | `https://generativelanguage.googleapis.com/v1beta`                                                                                                                                                                                       |
 | `MAX_FAILURES`                 | Optional, number of times a single key is allowed to fail                   | `3`                                                                                                                                                                                                                                      |
 | `MAX_RETRIES`                  | Optional, maximum number of retries for failed API requests                 | `3`                                                                                                                                                                                                                                      |
@@ -194,6 +205,10 @@ If you want to run the source code directly locally for development or testing,
 | `AUTO_DELETE_REQUEST_LOGS_ENABLED`| Optional, whether to enable automatic deletion of request logs             | `false`                                                                                                                                                                                                                                  |
 | `AUTO_DELETE_REQUEST_LOGS_DAYS` | Optional, automatically delete request logs older than this many days (e.g., 1, 7, 30) | `30`                                                                                                                                                                                                                                     |
 | `SAFETY_SETTINGS`              | Optional, safety settings (JSON string format), used to configure content safety thresholds. Example values may need adjustment based on actual model support. | `[{"category": "HARM_CATEGORY_HARASSMENT", "threshold": "OFF"}, {"category": "HARM_CATEGORY_HATE_SPEECH", "threshold": "OFF"}, {"category": "HARM_CATEGORY_SEXUALLY_EXPLICIT", "threshold": "OFF"}, {"category": "HARM_CATEGORY_DANGEROUS_CONTENT", "threshold": "OFF"}, {"category": "HARM_CATEGORY_CIVIC_INTEGRITY", "threshold": "BLOCK_NONE"}]` |
+| **TTS Related**                |                                                                             |                                                                                                                                                                                                                                          |
+| `TTS_MODEL`                    | Optional, TTS model name                                                    | `gemini-2.5-flash-preview-tts`                                                                                                                                                                                                           |
+| `TTS_VOICE_NAME`               | Optional, TTS voice name                                                    | `Zephyr`                                                                                                                                                                                                                                 |
+| `TTS_SPEED`                    | Optional, TTS speed                                                         | `normal`                                                                                                                                                                                                                                 |
 | **Image Generation Related**   |                                                                             |                                                                                                                                                                                                                                          |
 | `PAID_KEY`                     | Optional, paid API Key for advanced features like image generation          | `your-paid-api-key`                                                                                                                                                                                                                        |
 | `CREATE_IMAGE_MODEL`           | Optional, image generation model                                            | `imagen-3.0-generate-002`                                                                                                                                                                                                                  |
@@ -202,6 +217,7 @@ If you want to run the source code directly locally for development or testing,
 | `PICGO_API_KEY`                | Optional, API Key for [PicoGo](https://www.picgo.net/) image hosting        | `your-picogo-apikey`                                                                                                                                                                                                                         |
 | `CLOUDFLARE_IMGBED_URL`        | Optional, [CloudFlare](https://github.com/MarSeventh/CloudFlare-ImgBed) image hosting upload address | `https://xxxxxxx.pages.dev/upload`                                                                                                                                                                                           |
 | `CLOUDFLARE_IMGBED_AUTH_CODE`  | Optional, authentication key for CloudFlare image hosting                   | `your-cloudflare-imgber-auth-code`                                                                                                                                                                                                           |
+| `CLOUDFLARE_IMGBED_UPLOAD_FOLDER` | Optional, upload folder path for CloudFlare image hosting               | `""`                                                                                                                                                                                                                                          |
 | **Stream Optimizer Related**   |                                                                             |                                                                                                                                                                                                                                          |
 | `STREAM_OPTIMIZER_ENABLED`     | Optional, whether to enable stream output optimization                      | `false`                                                                                                                                                                                                                                  |
 | `STREAM_MIN_DELAY`             | Optional, minimum delay for stream output                                   | `0.016`                                                                                                                                                                                                                                  |
@@ -219,20 +235,20 @@ The following are the main API endpoints provided by the service:
 
 ### Gemini API Related (`(/gemini)/v1beta`)
 
-*   `GET /models`: List available Gemini models.
+* `GET /models`: List available Gemini models.
-*   `POST /models/{model_name}:generateContent`: Generate content using the specified Gemini model.
+* `POST /models/{model_name}:generateContent`: Generate content using the specified Gemini model.
-*   `POST /models/{model_name}:streamGenerateContent`: Stream content generation using the specified Gemini model.
+* `POST /models/{model_name}:streamGenerateContent`: Stream content generation using the specified Gemini model.
 
 ### OpenAI API Related
 
-*   `GET (/hf)/v1/models`: List available models (uses Gemini format underneath).
+* `GET (/hf)/v1/models`: List available models (uses Gemini format underneath).
-*   `POST (/hf)/v1/chat/completions`: Perform chat completion (uses Gemini format underneath, supports streaming).
+* `POST (/hf)/v1/chat/completions`: Perform chat completion (uses Gemini format underneath, supports streaming).
-*   `POST (/hf)/v1/embeddings`: Create text embeddings (uses Gemini format underneath).
+* `POST (/hf)/v1/embeddings`: Create text embeddings (uses Gemini format underneath).
-*   `POST (/hf)/v1/images/generations`: Generate images (uses Gemini format underneath).
+* `POST (/hf)/v1/images/generations`: Generate images (uses Gemini format underneath).
-*   `GET /openai/v1/models`: List available models (uses OpenAI format underneath).
+* `GET /openai/v1/models`: List available models (uses OpenAI format underneath).
-*   `POST /openai/v1/chat/completions`: Perform chat completion (uses OpenAI format underneath, supports streaming, can prevent truncation, and is faster).
+* `POST /openai/v1/chat/completions`: Perform chat completion (uses OpenAI format underneath, supports streaming, can prevent truncation, and is faster).
-*   `POST /openai/v1/embeddings`: Create text embeddings (uses OpenAI format underneath).
+* `POST /openai/v1/embeddings`: Create text embeddings (uses OpenAI format underneath).
-*   `POST /openai/v1/images/generations`: Generate images (uses OpenAI format underneath).
+* `POST /openai/v1/images/generations`: Generate images (uses OpenAI format underneath).
 
 ## 🤝 Contributing
 
@@ -242,9 +258,9 @@ Pull Requests or Issues are welcome.
 
 Special thanks to the following projects and platforms for providing image hosting services for this project:
 
-*   [PicGo](https://www.picgo.net/)
+* [PicGo](https://www.picgo.net/)
-*   [SM.MS](https://smms.app/)
+* [SM.MS](https://smms.app/)
-*   [CloudFlare-ImgBed](https://github.com/MarSeventh/CloudFlare-ImgBed) open source project
+* [CloudFlare-ImgBed](https://github.com/MarSeventh/CloudFlare-ImgBed) open source project
 
 ## 🙏 Thanks to Contributors
 
@@ -252,22 +268,26 @@ Thanks to all developers who contributed to this project!
 
 [![Contributors](https://contrib.rocks/image?repo=snailyp/gemini-balance)](https://github.com/snailyp/gemini-balance/graphs/contributors)
 
+## Thanks to Our Supporters
+
+A special shout-out to DigitalOcean for providing the rock-solid and dependable cloud infrastructure that keeps this project humming!
+[![DigitalOcean Logo](files/dataocean.svg)](https://m.do.co/c/b249dd7f3b4c)
+
+CDN acceleration and security protection for this project are sponsored by Tencent EdgeOne.
+[![EdgeOne Logo](https://edgeone.ai/media/34fe3a45-492d-4ea4-ae5d-ea1087ca7b4b.png)](https://edgeone.ai/?from=github)
+
 ## ⭐ Star History
 
 [![Star History Chart](https://api.star-history.com/svg?repos=snailyp/gemini-balance&type=Date)](https://star-history.com/#snailyp/gemini-balance&Date)
 
 ## 💖 Friendly Projects
 
-*   **[OneLine](https://github.com/chengtx809/OneLine)** by [chengtx809](https://github.com/chengtx809) - OneLine: AI-driven hot event timeline generation tool
+* **[OneLine](https://github.com/chengtx809/OneLine)** by [chengtx809](https://github.com/chengtx809) - OneLine: AI-driven hot event timeline generation tool
 
 ## 🎁 Project Support
 
 If you find this project helpful, consider supporting me via [Afdian](https://afdian.com/a/snaily).
 
-## VPS Recommend
-
-[![Powered by DartNode](https://dartnode.com/branding/DN-Open-Source-sm.png)](https://dartnode.com "Powered by DartNode - Free VPS for Open Source")
-
 ## License
 
 This project is licensed under the CC BY-NC 4.0 (Attribution-NonCommercial) license. Any form of commercial resale service is prohibited. See the LICENSE file for details.

README_ZH.md

@@ -1,5 +1,11 @@
 # Gemini Balance - Gemini API 代理和负载均衡器
 
+<p align="center">
+  <a href="https://trendshift.io/repositories/13692" target="_blank">
+    <img src="https://trendshift.io/api/badge/repositories/13692" alt="snailyp%2Fgemini-balance | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/>
+  </a>
+</p>
+
 > ⚠️ 本项目采用 CC BY-NC 4.0（署名-非商业性使用）协议，禁止任何形式的商业倒卖服务，详见 LICENSE 文件。
 
 > 本人从未在各个平台售卖服务，如有遇到售卖此服务者，那一定是倒卖狗，大家切记不要上当受骗。
@@ -178,6 +184,7 @@ app/
 | `SHOW_THINKING_PROCESS`      | 可选，是否显示模型思考过程                                     | `true`                                                |
 | `THINKING_MODELS`            | 可选，支持思考功能的模型列表                                   | `[]`                                                  |
 | `THINKING_BUDGET_MAP`        | 可选，思考功能预算映射 (模型名:预算值)                         | `{}`                                                  |
+| `URL_NORMALIZATION_ENABLED`  | 可选，是否启用智能路由映射功能                                 | `false`                                               |
 | `BASE_URL`                   | 可选，Gemini API 基础 URL，默认无需修改                        | `https://generativelanguage.googleapis.com/v1beta`    |
 | `MAX_FAILURES`               | 可选，允许单个key失败的次数                                    | `3`                                                   |
 | `MAX_RETRIES`                | 可选，API 请求失败时的最大重试次数                             | `3`                                                   |
@@ -191,6 +198,10 @@ app/
 | `AUTO_DELETE_REQUEST_LOGS_ENABLED`| 可选，是否开启自动删除请求日志                               | `false`                                               |
 | `AUTO_DELETE_REQUEST_LOGS_DAYS` | 可选，自动删除多少天前的请求日志 (例如 1, 7, 30)           | `30`                                                  |
 | `SAFETY_SETTINGS`            | 可选，安全设置 (JSON 字符串格式)，用于配置内容安全阈值。示例值可能需要根据实际模型支持情况调整。 | `[{"category": "HARM_CATEGORY_HARASSMENT", "threshold": "OFF"}, {"category": "HARM_CATEGORY_HATE_SPEECH", "threshold": "OFF"}, {"category": "HARM_CATEGORY_SEXUALLY_EXPLICIT", "threshold": "OFF"}, {"category": "HARM_CATEGORY_DANGEROUS_CONTENT", "threshold": "OFF"}, {"category": "HARM_CATEGORY_CIVIC_INTEGRITY", "threshold": "BLOCK_NONE"}]` |
+| **TTS 相关**                 |                                                          |                                                       |
+| `TTS_MODEL`                  | 可选，TTS 模型名称                                           | `gemini-2.5-flash-preview-tts`                        |
+| `TTS_VOICE_NAME`             | 可选，TTS 语音名称                                           | `Zephyr`                                              |
+| `TTS_SPEED`                  | 可选，TTS 语速                                               | `normal`                                              |
 | **图像生成相关**             |                                                          |                                                       |
 | `PAID_KEY`                   | 可选，付费版API Key，用于图片生成等高级功能                    | `your-paid-api-key`                                   |
 | `CREATE_IMAGE_MODEL`         | 可选，图片生成模型                                             | `imagen-3.0-generate-002`                             |
@@ -199,6 +210,7 @@ app/
 | `PICGO_API_KEY`              | 可选，[PicoGo](https://www.picgo.net/)图床的API Key                                      | `your-picogo-apikey`                                  |
 | `CLOUDFLARE_IMGBED_URL`      | 可选，[CloudFlare](https://github.com/MarSeventh/CloudFlare-ImgBed) 图床上传地址                                  | `https://xxxxxxx.pages.dev/upload`                    |
 | `CLOUDFLARE_IMGBED_AUTH_CODE`| 可选，CloudFlare图床的鉴权key                                  | `your-cloudflare-imgber-auth-code`                    |
+| `CLOUDFLARE_IMGBED_UPLOAD_FOLDER`| 可选，CloudFlare图床的上传文件夹路径                        | `""`                                                  |
 | **流式优化器相关**           |                                                          |                                                       |
 | `STREAM_OPTIMIZER_ENABLED`   | 可选，是否启用流式输出优化                                     | `false`                                               |
 | `STREAM_MIN_DELAY`           | 可选，流式输出最小延迟                                         | `0.016`                                               |

VERSION

@@ -1 +1 @@
-2.1.5
+2.1.8

app/config/config.py

@@ -60,9 +60,13 @@ class Settings(BaseSettings):
     TIME_OUT: int = DEFAULT_TIMEOUT
     MAX_RETRIES: int = MAX_RETRIES
     PROXIES: List[str] = []
+    PROXIES_USE_CONSISTENCY_HASH_BY_API_KEY: bool = True  # 是否使用一致性哈希来选择代理
     VERTEX_API_KEYS: List[str] = []
     VERTEX_EXPRESS_BASE_URL: str = "https://aiplatform.googleapis.com/v1beta1/publishers/google"
- 
+
+    # 智能路由配置
+    URL_NORMALIZATION_ENABLED: bool = False  # 是否启用智能路由映射功能
+
     # 模型相关配置
     SEARCH_MODELS: List[str] = ["gemini-2.0-flash-exp"]
     IMAGE_MODELS: List[str] = ["gemini-2.0-flash-exp"]
@@ -73,6 +77,11 @@ class Settings(BaseSettings):
     THINKING_MODELS: List[str] = []
     THINKING_BUDGET_MAP: Dict[str, float] = {}
 
+    # TTS相关配置
+    TTS_MODEL: str = "gemini-2.5-flash-preview-tts"
+    TTS_VOICE_NAME: str = "Zephyr"
+    TTS_SPEED: str = "normal"
+
     # 图像生成相关配置
     PAID_KEY: str = ""
     CREATE_IMAGE_MODEL: str = DEFAULT_CREATE_IMAGE_MODEL
@@ -81,6 +90,7 @@ class Settings(BaseSettings):
     PICGO_API_KEY: str = ""
     CLOUDFLARE_IMGBED_URL: str = ""
     CLOUDFLARE_IMGBED_AUTH_CODE: str = ""
+    CLOUDFLARE_IMGBED_UPLOAD_FOLDER: str = ""
 
     # 流式输出优化器配置
     STREAM_OPTIMIZER_ENABLED: bool = False
@@ -110,6 +120,7 @@ class Settings(BaseSettings):
     AUTO_DELETE_REQUEST_LOGS_DAYS: int = 30
     SAFETY_SETTINGS: List[Dict[str, str]] = DEFAULT_SAFETY_SETTINGS
 
+
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
         # 设置默认AUTH_TOKEN（如果未提供）

app/database/connection.py

@@ -2,6 +2,7 @@
 数据库连接池模块
 """
 from pathlib import Path
+from urllib.parse import quote_plus
 from databases import Database
 from sqlalchemy import create_engine, MetaData
 from sqlalchemy.ext.declarative import declarative_base
@@ -20,9 +21,9 @@ if settings.DATABASE_TYPE == "sqlite":
     DATABASE_URL = f"sqlite:///{db_path}"
 elif settings.DATABASE_TYPE == "mysql":
     if settings.MYSQL_SOCKET:
-        DATABASE_URL = f"mysql+pymysql://{settings.MYSQL_USER}:{settings.MYSQL_PASSWORD}@/{settings.MYSQL_DATABASE}?unix_socket={settings.MYSQL_SOCKET}"
+        DATABASE_URL = f"mysql+pymysql://{settings.MYSQL_USER}:{quote_plus(settings.MYSQL_PASSWORD)}@/{settings.MYSQL_DATABASE}?unix_socket={settings.MYSQL_SOCKET}"
     else:
-        DATABASE_URL = f"mysql+pymysql://{settings.MYSQL_USER}:{settings.MYSQL_PASSWORD}@{settings.MYSQL_HOST}:{settings.MYSQL_PORT}/{settings.MYSQL_DATABASE}"
+        DATABASE_URL = f"mysql+pymysql://{settings.MYSQL_USER}:{quote_plus(settings.MYSQL_PASSWORD)}@{settings.MYSQL_HOST}:{settings.MYSQL_PORT}/{settings.MYSQL_DATABASE}"
 else:
     raise ValueError("Unsupported database type. Please set DATABASE_TYPE to 'sqlite' or 'mysql'.")
 

app/domain/gemini_models.py

@@ -44,12 +44,12 @@ class GenerationConfig(BaseModel):
 
 
 class SystemInstruction(BaseModel):
-    role: str = "system"
+    role: Optional[str] = "system"
-    parts: List[Dict[str, Any]] | Dict[str, Any]
+    parts: Union[List[Dict[str, Any]], Dict[str, Any]]
 
 
 class GeminiContent(BaseModel):
-    role: str
+    role: Optional[str] = None
     parts: List[Dict[str, Any]]
 
 

app/domain/image_models.py

@@ -1,23 +1,20 @@
+from typing import Union
+
+
 class ImageMetadata:
-    def __init__(self, width: int, height: int, filename: str, size: int, url: str, delete_url: str | None = None):
+    def __init__(self, width: int, height: int, filename: str, size: int, url: str, delete_url: Union[str, None] = None):
         self.width = width
         self.height = height
         self.filename = filename
         self.size = size
         self.url = url
         self.delete_url = delete_url
-    
-    
 class UploadResponse:
     def __init__(self, success: bool, code: str, message: str, data: ImageMetadata):
         self.success = success
         self.code = code
         self.message = message
         self.data = data
-    
-    
 class ImageUploader:
     def upload(self, file: bytes, filename: str) -> UploadResponse:
         raise NotImplementedError
-    
-    

app/domain/openai_models.py

@@ -33,3 +33,10 @@ class ImageGenerationRequest(BaseModel):
     quality: Optional[str] = None
     style: Optional[str] = None
     response_format: Optional[str] = "url"
+
+
+class TTSRequest(BaseModel):
+    model: str = "gemini-2.5-flash-preview-tts"
+    input: str
+    voice: str = "Kore"
+    response_format: Optional[str] = "wav"

app/handler/response_handler.py

@@ -238,6 +238,7 @@ def _extract_image_data(part: dict) -> str:
             provider=settings.UPLOAD_PROVIDER,
             base_url=settings.CLOUDFLARE_IMGBED_URL,
             auth_code=settings.CLOUDFLARE_IMGBED_AUTH_CODE,
+            upload_folder=settings.CLOUDFLARE_IMGBED_UPLOAD_FOLDER,
         )
     current_date = time.strftime("%Y/%m/%d")
     filename = f"{current_date}/{uuid.uuid4().hex[:8]}.png"

app/middleware/middleware.py

@@ -8,6 +8,7 @@ from fastapi.responses import RedirectResponse
 from starlette.middleware.base import BaseHTTPMiddleware
 
 # from app.middleware.request_logging_middleware import RequestLoggingMiddleware
+from app.middleware.smart_routing_middleware import SmartRoutingMiddleware
 from app.core.constants import API_VERSION
 from app.core.security import verify_auth_token
 from app.log.logger import get_middleware_logger
@@ -52,6 +53,9 @@ def setup_middlewares(app: FastAPI) -> None:
     Args:
         app: FastAPI应用程序实例
     """
+    # 添加智能路由中间件（必须在认证中间件之前）
+    app.add_middleware(SmartRoutingMiddleware)
+
     # 添加认证中间件
     app.add_middleware(AuthMiddleware)
 

app/middleware/smart_routing_middleware.py

@@ -0,0 +1,210 @@
+from fastapi import Request
+from starlette.middleware.base import BaseHTTPMiddleware
+from app.config.config import settings
+from app.log.logger import get_main_logger
+import re
+
+logger = get_main_logger()
+
+class SmartRoutingMiddleware(BaseHTTPMiddleware):
+    def __init__(self, app):
+        super().__init__(app)
+        # 简化的路由规则 - 直接根据检测结果路由
+        pass
+
+    async def dispatch(self, request: Request, call_next):
+        if not settings.URL_NORMALIZATION_ENABLED:
+            return await call_next(request)
+        logger.debug(f"request: {request}")
+        original_path = str(request.url.path)
+        method = request.method
+        
+        # 尝试修复URL
+        fixed_path, fix_info = self.fix_request_url(original_path, method, request)
+
+        if fixed_path != original_path:
+            logger.info(f"URL fixed: {method} {original_path} → {fixed_path}")
+            if fix_info:
+                logger.debug(f"Fix details: {fix_info}")
+
+            # 重写请求路径
+            request.scope["path"] = fixed_path
+            request.scope["raw_path"] = fixed_path.encode()
+        
+        return await call_next(request)
+
+    def fix_request_url(self, path: str, method: str, request: Request) -> tuple:
+        """简化的URL修复逻辑"""
+
+        # 首先检查是否已经是正确的格式，如果是则不处理
+        if self.is_already_correct_format(path):
+            return path, None
+
+        # 1. 最高优先级：包含generateContent → Gemini格式
+        if "generatecontent" in path.lower() or "v1beta/models" in path.lower():
+            return self.fix_gemini_by_operation(path, method, request)
+
+        # 2. 第二优先级：包含/openai/ → OpenAI格式
+        if "/openai/" in path.lower():
+            return self.fix_openai_by_operation(path, method)
+
+        # 3. 第三优先级：包含/v1/ → v1格式
+        if "/v1/" in path.lower():
+            return self.fix_v1_by_operation(path, method)
+
+        # 4. 第四优先级：包含/chat/completions → chat功能
+        if "/chat/completions" in path.lower():
+            return "/v1/chat/completions", {"type": "v1_chat"}
+
+        # 5. 默认：原样传递
+        return path, None
+
+    def is_already_correct_format(self, path: str) -> bool:
+        """检查是否已经是正确的API格式"""
+        # 检查是否已经是正确的端点格式
+        correct_patterns = [
+            r"^/v1beta/models/[^/:]+:(generate|streamGenerate)Content$",  # Gemini原生
+            r"^/gemini/v1beta/models/[^/:]+:(generate|streamGenerate)Content$",  # Gemini带前缀
+            r"^/v1beta/models$",  # Gemini模型列表
+            r"^/gemini/v1beta/models$",  # Gemini带前缀的模型列表
+            r"^/v1/(chat/completions|models|embeddings|images/generations|audio/speech)$",  # v1格式
+            r"^/openai/v1/(chat/completions|models|embeddings|images/generations|audio/speech)$",  # OpenAI格式
+            r"^/hf/v1/(chat/completions|models|embeddings|images/generations|audio/speech)$",  # HF格式
+            r"^/vertex-express/v1beta/models/[^/:]+:(generate|streamGenerate)Content$",  # Vertex Express Gemini格式
+            r"^/vertex-express/v1beta/models$",  # Vertex Express模型列表
+            r"^/vertex-express/v1/(chat/completions|models|embeddings|images/generations)$",  # Vertex Express OpenAI格式
+        ]
+
+        for pattern in correct_patterns:
+            if re.match(pattern, path):
+                return True
+
+        return False
+
+    def fix_gemini_by_operation(
+        self, path: str, method: str, request: Request
+    ) -> tuple:
+        """根据Gemini操作修复，考虑端点偏好"""
+        if method == "GET":
+            return "/v1beta/models", {
+                "role": "gemini_models",
+            }
+
+        # 提取模型名称
+        try:
+            model_name = self.extract_model_name(path, request)
+        except ValueError:
+            # 无法提取模型名称，返回原路径不做处理
+            return path, None
+
+        # 检测是否为流式请求
+        is_stream = self.detect_stream_request(path, request)
+
+        # 检查是否有vertex-express偏好
+        if "/vertex-express/" in path.lower():
+            if is_stream:
+                target_url = (
+                    f"/vertex-express/v1beta/models/{model_name}:streamGenerateContent"
+                )
+            else:
+                target_url = (
+                    f"/vertex-express/v1beta/models/{model_name}:generateContent"
+                )
+
+            fix_info = {
+                "rule": (
+                    "vertex_express_generate"
+                    if not is_stream
+                    else "vertex_express_stream"
+                ),
+                "preference": "vertex_express_format",
+                "is_stream": is_stream,
+                "model": model_name,
+            }
+        else:
+            # 标准Gemini端点
+            if is_stream:
+                target_url = f"/v1beta/models/{model_name}:streamGenerateContent"
+            else:
+                target_url = f"/v1beta/models/{model_name}:generateContent"
+
+            fix_info = {
+                "rule": "gemini_generate" if not is_stream else "gemini_stream",
+                "preference": "gemini_format",
+                "is_stream": is_stream,
+                "model": model_name,
+            }
+
+        return target_url, fix_info
+
+    def fix_openai_by_operation(self, path: str, method: str) -> tuple:
+        """根据操作类型修复OpenAI格式"""
+        if method == "POST":
+            if "chat" in path.lower() or "completion" in path.lower():
+                return "/openai/v1/chat/completions", {"type": "openai_chat"}
+            elif "embedding" in path.lower():
+                return "/openai/v1/embeddings", {"type": "openai_embeddings"}
+            elif "image" in path.lower():
+                return "/openai/v1/images/generations", {"type": "openai_images"}
+            elif "audio" in path.lower():
+                return "/openai/v1/audio/speech", {"type": "openai_audio"}
+        elif method == "GET":
+            if "model" in path.lower():
+                return "/openai/v1/models", {"type": "openai_models"}
+
+        return path, None
+
+    def fix_v1_by_operation(self, path: str, method: str) -> tuple:
+        """根据操作类型修复v1格式"""
+        if method == "POST":
+            if "chat" in path.lower() or "completion" in path.lower():
+                return "/v1/chat/completions", {"type": "v1_chat"}
+            elif "embedding" in path.lower():
+                return "/v1/embeddings", {"type": "v1_embeddings"}
+            elif "image" in path.lower():
+                return "/v1/images/generations", {"type": "v1_images"}
+            elif "audio" in path.lower():
+                return "/v1/audio/speech", {"type": "v1_audio"}
+        elif method == "GET":
+            if "model" in path.lower():
+                return "/v1/models", {"type": "v1_models"}
+
+        return path, None
+
+    def detect_stream_request(self, path: str, request: Request) -> bool:
+        """检测是否为流式请求"""
+        # 1. 路径中包含stream关键词
+        if "stream" in path.lower():
+            return True
+
+        # 2. 查询参数
+        if request.query_params.get("stream") == "true":
+            return True
+
+        return False
+
+    def extract_model_name(self, path: str, request: Request) -> str:
+        """从请求中提取模型名称，用于构建Gemini API URL"""
+        # 1. 从请求体中提取
+        try:
+            if hasattr(request, "_body") and request._body:
+                import json
+
+                body = json.loads(request._body.decode())
+                if "model" in body and body["model"]:
+                    return body["model"]
+        except Exception:
+            pass
+
+        # 2. 从查询参数中提取
+        model_param = request.query_params.get("model")
+        if model_param:
+            return model_param
+
+        # 3. 从路径中提取（用于已包含模型名称的路径）
+        match = re.search(r"/models/([^/:]+)", path, re.IGNORECASE)
+        if match:
+            return match.group(1)
+
+        # 4. 如果无法提取模型名称，抛出异常
+        raise ValueError("Unable to extract model name from request")

app/router/gemini_routes.py

@@ -151,6 +151,35 @@ async def stream_generate_content(
         return StreamingResponse(response_stream, media_type="text/event-stream")
 
 
+@router.post("/models/{model_name}:countTokens")
+@router_v1beta.post("/models/{model_name}:countTokens")
+@RetryHandler(key_arg="api_key")
+async def count_tokens(
+    model_name: str,
+    request: GeminiRequest,
+    _=Depends(security_service.verify_key_or_goog_api_key),
+    api_key: str = Depends(get_next_working_key),
+    key_manager: KeyManager = Depends(get_key_manager),
+    chat_service: GeminiChatService = Depends(get_chat_service)
+):
+    """处理 Gemini token 计数请求。"""
+    operation_name = "gemini_count_tokens"
+    async with handle_route_errors(logger, operation_name, failure_message="Token counting failed"):
+        logger.info(f"Handling Gemini token count request for model: {model_name}")
+        logger.debug(f"Request: \n{request.model_dump_json(indent=2)}")
+        logger.info(f"Using API key: {api_key}")
+
+        if not await model_service.check_model_support(model_name):
+            raise HTTPException(status_code=400, detail=f"Model {model_name} is not supported")
+
+        response = await chat_service.count_tokens(
+            model=model_name,
+            request=request,
+            api_key=api_key
+        )
+        return response
+
+
 @router.post("/reset-all-fail-counts")
 async def reset_all_key_fail_counts(key_type: str = None, key_manager: KeyManager = Depends(get_key_manager)):
     """批量重置Gemini API密钥的失败计数，可选择性地仅重置有效或无效密钥"""

app/router/openai_routes.py

@@ -1,4 +1,4 @@
-from fastapi import APIRouter, Depends, HTTPException
+from fastapi import APIRouter, Depends, HTTPException, Response
 from fastapi.responses import StreamingResponse
 
 from app.config.config import settings
@@ -7,6 +7,7 @@ from app.domain.openai_models import (
     ChatRequest,
     EmbeddingRequest,
     ImageGenerationRequest,
+    TTSRequest,
 )
 from app.handler.retry_handler import RetryHandler
 from app.handler.error_handler import handle_route_errors
@@ -14,6 +15,7 @@ from app.log.logger import get_openai_logger
 from app.service.chat.openai_chat_service import OpenAIChatService
 from app.service.embedding.embedding_service import EmbeddingService
 from app.service.image.image_create_service import ImageCreateService
+from app.service.tts.tts_service import TTSService
 from app.service.key.key_manager import KeyManager, get_key_manager_instance
 from app.service.model.model_service import ModelService
 
@@ -24,6 +26,7 @@ security_service = SecurityService()
 model_service = ModelService()
 embedding_service = EmbeddingService()
 image_create_service = ImageCreateService()
+tts_service = TTSService()
 
 
 async def get_key_manager():
@@ -41,6 +44,11 @@ async def get_openai_chat_service(key_manager: KeyManager = Depends(get_key_mana
     return OpenAIChatService(settings.BASE_URL, key_manager)
 
 
+async def get_tts_service():
+    """获取TTS服务实例"""
+    return tts_service
+
+
 @router.get("/v1/models")
 @router.get("/hf/v1/models")
 async def list_models(
@@ -147,3 +155,21 @@ async def get_keys_list(
             },
             "total": len(keys_status["valid_keys"]) + len(keys_status["invalid_keys"]),
         }
+
+
+@router.post("/v1/audio/speech")
+@router.post("/hf/v1/audio/speech")
+async def text_to_speech(
+    request: TTSRequest,
+    _=Depends(security_service.verify_authorization),
+    api_key: str = Depends(get_next_working_key_wrapper),
+    tts_service: TTSService = Depends(get_tts_service),
+):
+    """处理 OpenAI TTS 请求。"""
+    operation_name = "text_to_speech"
+    async with handle_route_errors(logger, operation_name):
+        logger.info(f"Handling TTS request for model: {request.model}")
+        logger.debug(f"Request: \n{request.model_dump_json(indent=2)}")
+        logger.info(f"Using API key: {api_key}")
+        audio_data = await tts_service.create_tts(request, api_key)
+        return Response(content=audio_data, media_type="audio/wav")

app/service/chat/gemini_chat_service.py

@@ -195,6 +195,54 @@ class GeminiChatService:
                 request_time=request_datetime
             )
 
+    async def count_tokens(
+        self, model: str, request: GeminiRequest, api_key: str
+    ) -> Dict[str, Any]:
+        """计算token数量"""
+        # countTokens API只需要contents
+        payload = {"contents": request.model_dump().get("contents", [])}
+        start_time = time.perf_counter()
+        request_datetime = datetime.datetime.now()
+        is_success = False
+        status_code = None
+        response = None
+
+        try:
+            response = await self.api_client.count_tokens(payload, model, api_key)
+            is_success = True
+            status_code = 200
+            return response
+        except Exception as e:
+            is_success = False
+            error_log_msg = str(e)
+            logger.error(f"Count tokens API call failed with error: {error_log_msg}")
+            match = re.search(r"status code (\d+)", error_log_msg)
+            if match:
+                status_code = int(match.group(1))
+            else:
+                status_code = 500
+
+            await add_error_log(
+                gemini_key=api_key,
+                model_name=model,
+                error_type="gemini-count-tokens",
+                error_log=error_log_msg,
+                error_code=status_code,
+                request_msg=payload
+            )
+            raise e
+        finally:
+            end_time = time.perf_counter()
+            latency_ms = int((end_time - start_time) * 1000)
+            await add_request_log(
+                model_name=model,
+                api_key=api_key,
+                is_success=is_success,
+                status_code=status_code,
+                latency_ms=latency_ms,
+                request_time=request_datetime
+            )
+
     async def stream_generate_content(
         self, model: str, request: GeminiRequest, api_key: str
     ) -> AsyncGenerator[str, None]:

app/service/client/api_client.py

@@ -21,6 +21,10 @@ class ApiClient(ABC):
     async def stream_generate_content(self, payload: Dict[str, Any], model: str, api_key: str) -> AsyncGenerator[str, None]:
         pass
 
+    @abstractmethod
+    async def count_tokens(self, payload: Dict[str, Any], model: str, api_key: str) -> Dict[str, Any]:
+        pass
+
 
 class GeminiApiClient(ApiClient):
     """Gemini API客户端"""
@@ -46,11 +50,14 @@ class GeminiApiClient(ApiClient):
         
         proxy_to_use = None
         if settings.PROXIES:
-            proxy_to_use = random.choice(settings.PROXIES)
+            if settings.PROXIES_USE_CONSISTENCY_HASH_BY_API_KEY:
+                proxy_to_use = settings.PROXIES[hash(api_key) % len(settings.PROXIES)]
+            else:
+                proxy_to_use = random.choice(settings.PROXIES)
             logger.info(f"Using proxy for getting models: {proxy_to_use}")
 
         async with httpx.AsyncClient(timeout=timeout, proxy=proxy_to_use) as client:
-            url = f"{self.base_url}/models?key={api_key}"
+            url = f"{self.base_url}/models?key={api_key}&pageSize=1000"
             try:
                 response = await client.get(url)
                 response.raise_for_status()
@@ -69,8 +76,11 @@ class GeminiApiClient(ApiClient):
 
         proxy_to_use = None
         if settings.PROXIES:
-            proxy_to_use = random.choice(settings.PROXIES)
+            if settings.PROXIES_USE_CONSISTENCY_HASH_BY_API_KEY:
-            logger.info(f"Using proxy: {proxy_to_use}")
+                proxy_to_use = settings.PROXIES[hash(api_key) % len(settings.PROXIES)]
+            else:
+                proxy_to_use = random.choice(settings.PROXIES)
+            logger.info(f"Using proxy for getting models: {proxy_to_use}")
             
         async with httpx.AsyncClient(timeout=timeout, proxy=proxy_to_use) as client:
             url = f"{self.base_url}/models/{model}:generateContent?key={api_key}"
@@ -86,8 +96,11 @@ class GeminiApiClient(ApiClient):
         
         proxy_to_use = None
         if settings.PROXIES:
-            proxy_to_use = random.choice(settings.PROXIES)
+            if settings.PROXIES_USE_CONSISTENCY_HASH_BY_API_KEY:
-            logger.info(f"Using proxy: {proxy_to_use}")
+                proxy_to_use = settings.PROXIES[hash(api_key) % len(settings.PROXIES)]
+            else:
+                proxy_to_use = random.choice(settings.PROXIES)
+            logger.info(f"Using proxy for getting models: {proxy_to_use}")
 
         async with httpx.AsyncClient(timeout=timeout, proxy=proxy_to_use) as client:
             url = f"{self.base_url}/models/{model}:streamGenerateContent?alt=sse&key={api_key}"
@@ -99,6 +112,26 @@ class GeminiApiClient(ApiClient):
                 async for line in response.aiter_lines():
                     yield line
 
+    async def count_tokens(self, payload: Dict[str, Any], model: str, api_key: str) -> Dict[str, Any]:
+        timeout = httpx.Timeout(self.timeout, read=self.timeout)
+        model = self._get_real_model(model)
+
+        proxy_to_use = None
+        if settings.PROXIES:
+            if settings.PROXIES_USE_CONSISTENCY_HASH_BY_API_KEY:
+                proxy_to_use = settings.PROXIES[hash(api_key) % len(settings.PROXIES)]
+            else:
+                proxy_to_use = random.choice(settings.PROXIES)
+            logger.info(f"Using proxy for counting tokens: {proxy_to_use}")
+
+        async with httpx.AsyncClient(timeout=timeout, proxy=proxy_to_use) as client:
+            url = f"{self.base_url}/models/{model}:countTokens?key={api_key}"
+            response = await client.post(url, json=payload)
+            if response.status_code != 200:
+                error_content = response.text
+                raise Exception(f"API call failed with status code {response.status_code}, {error_content}")
+            return response.json()
+
 
 class OpenaiApiClient(ApiClient):
     """OpenAI API客户端"""
@@ -109,7 +142,16 @@ class OpenaiApiClient(ApiClient):
         
     async def get_models(self, api_key: str) -> Dict[str, Any]:
         timeout = httpx.Timeout(self.timeout, read=self.timeout)
-        async with httpx.AsyncClient(timeout=timeout) as client:
+
+        proxy_to_use = None
+        if settings.PROXIES:
+            if settings.PROXIES_USE_CONSISTENCY_HASH_BY_API_KEY:
+                proxy_to_use = settings.PROXIES[hash(api_key) % len(settings.PROXIES)]
+            else:
+                proxy_to_use = random.choice(settings.PROXIES)
+            logger.info(f"Using proxy for getting models: {proxy_to_use}")
+
+        async with httpx.AsyncClient(timeout=timeout, proxy=proxy_to_use) as client:
             url = f"{self.base_url}/openai/models"
             headers = {"Authorization": f"Bearer {api_key}"}
             response = await client.get(url, headers=headers)
@@ -120,11 +162,14 @@ class OpenaiApiClient(ApiClient):
 
     async def generate_content(self, payload: Dict[str, Any], api_key: str) -> Dict[str, Any]:
         timeout = httpx.Timeout(self.timeout, read=self.timeout)
-        
+        logger.info(f"settings.PROXIES_USE_CONSISTENCY_HASH_BY_API_KEY: {settings.PROXIES_USE_CONSISTENCY_HASH_BY_API_KEY}")
         proxy_to_use = None
         if settings.PROXIES:
-            proxy_to_use = random.choice(settings.PROXIES)
+            if settings.PROXIES_USE_CONSISTENCY_HASH_BY_API_KEY:
-            logger.info(f"Using proxy: {proxy_to_use}")
+                proxy_to_use = settings.PROXIES[hash(api_key) % len(settings.PROXIES)]
+            else:
+                proxy_to_use = random.choice(settings.PROXIES)
+            logger.info(f"Using proxy for getting models: {proxy_to_use}")
 
         async with httpx.AsyncClient(timeout=timeout, proxy=proxy_to_use) as client:
             url = f"{self.base_url}/openai/chat/completions"
@@ -137,11 +182,13 @@ class OpenaiApiClient(ApiClient):
 
     async def stream_generate_content(self, payload: Dict[str, Any], api_key: str) -> AsyncGenerator[str, None]:
         timeout = httpx.Timeout(self.timeout, read=self.timeout)
-        
         proxy_to_use = None
         if settings.PROXIES:
-            proxy_to_use = random.choice(settings.PROXIES)
+            if settings.PROXIES_USE_CONSISTENCY_HASH_BY_API_KEY:
-            logger.info(f"Using proxy: {proxy_to_use}")
+                proxy_to_use = settings.PROXIES[hash(api_key) % len(settings.PROXIES)]
+            else:
+                proxy_to_use = random.choice(settings.PROXIES)
+            logger.info(f"Using proxy for getting models: {proxy_to_use}")
 
         async with httpx.AsyncClient(timeout=timeout, proxy=proxy_to_use) as client:
             url = f"{self.base_url}/openai/chat/completions"
@@ -159,8 +206,11 @@ class OpenaiApiClient(ApiClient):
         
         proxy_to_use = None
         if settings.PROXIES:
-            proxy_to_use = random.choice(settings.PROXIES)
+            if settings.PROXIES_USE_CONSISTENCY_HASH_BY_API_KEY:
-            logger.info(f"Using proxy: {proxy_to_use}")
+                proxy_to_use = settings.PROXIES[hash(api_key) % len(settings.PROXIES)]
+            else:
+                proxy_to_use = random.choice(settings.PROXIES)
+            logger.info(f"Using proxy for getting models: {proxy_to_use}")
 
         async with httpx.AsyncClient(timeout=timeout, proxy=proxy_to_use) as client:
             url = f"{self.base_url}/openai/embeddings"
@@ -177,11 +227,14 @@ class OpenaiApiClient(ApiClient):
                     
     async def generate_images(self, payload: Dict[str, Any], api_key: str) -> Dict[str, Any]:
         timeout = httpx.Timeout(self.timeout, read=self.timeout)
-        
+
         proxy_to_use = None
         if settings.PROXIES:
-            proxy_to_use = random.choice(settings.PROXIES)
+            if settings.PROXIES_USE_CONSISTENCY_HASH_BY_API_KEY:
-            logger.info(f"Using proxy: {proxy_to_use}")
+                proxy_to_use = settings.PROXIES[hash(api_key) % len(settings.PROXIES)]
+            else:
+                proxy_to_use = random.choice(settings.PROXIES)
+            logger.info(f"Using proxy for getting models: {proxy_to_use}")
 
         async with httpx.AsyncClient(timeout=timeout, proxy=proxy_to_use) as client:
             url = f"{self.base_url}/openai/images/generations"

app/service/image/image_create_service.py

@@ -121,6 +121,7 @@ class ImageCreateService:
                             provider=settings.UPLOAD_PROVIDER,
                             base_url=settings.CLOUDFLARE_IMGBED_URL,
                             auth_code=settings.CLOUDFLARE_IMGBED_AUTH_CODE,
+                            upload_folder=settings.CLOUDFLARE_IMGBED_UPLOAD_FOLDER,
                         )
                     else:
                         raise ValueError(

app/service/key/key_manager.py

@@ -1,6 +1,6 @@
 import asyncio
 from itertools import cycle
-from typing import Dict
+from typing import Dict, Union
 
 from app.config.config import settings
 from app.log.logger import get_key_manager_logger
@@ -178,19 +178,20 @@ class KeyManager:
         if self.api_keys:
             return self.api_keys[0]
         if not self.api_keys:
-            logger.warning("API key list is empty, cannot get first valid key.")
+            logger.warning(
+                "API key list is empty, cannot get first valid key.")
             return ""
         return self.api_keys[0]
 
 
 _singleton_instance = None
 _singleton_lock = asyncio.Lock()
-_preserved_failure_counts: Dict[str, int] | None = None
+_preserved_failure_counts: Union[Dict[str, int], None] = None
-_preserved_vertex_failure_counts: Dict[str, int] | None = None
+_preserved_vertex_failure_counts: Union[Dict[str, int], None] = None
-_preserved_old_api_keys_for_reset: list | None = None
+_preserved_old_api_keys_for_reset: Union[list, None] = None
-_preserved_vertex_old_api_keys_for_reset: list | None = None
+_preserved_vertex_old_api_keys_for_reset: Union[list, None] = None
-_preserved_next_key_in_cycle: str | None = None
+_preserved_next_key_in_cycle: Union[str, None] = None
-_preserved_vertex_next_key_in_cycle: str | None = None
+_preserved_vertex_next_key_in_cycle: Union[str, None] = None
 
 
 async def get_key_manager_instance(
@@ -252,7 +253,8 @@ async def get_key_manager_instance(
                 _singleton_instance.vertex_key_failure_counts = (
                     current_vertex_failure_counts
                 )
-                logger.info("Inherited failure counts for applicable Vertex keys.")
+                logger.info(
+                    "Inherited failure counts for applicable Vertex keys.")
             _preserved_vertex_failure_counts = None
 
             # 2. 调整 key_cycle 的起始点
@@ -357,7 +359,7 @@ async def get_key_manager_instance(
                         f"Error determining start key for new Vertex key cycle from preserved state: {e}. "
                         "New cycle will start from the beginning."
                     )
-                
+
             if start_key_for_new_vertex_cycle and _singleton_instance.vertex_api_keys:
                 try:
                     target_idx = _singleton_instance.vertex_api_keys.index(
@@ -380,7 +382,7 @@ async def get_key_manager_instance(
                 except Exception as e:
                     logger.error(
                         f"Error advancing new Vertex key cycle: {e}. Cycle will start from beginning."
-                    ) 
+                    )
             else:
                 if _singleton_instance.vertex_api_keys:
                     logger.info(
@@ -418,7 +420,7 @@ async def reset_key_manager_instance():
             # 3. 保存 key_cycle 的下一个 key 提示
             try:
                 if _singleton_instance.api_keys:
-                    _preserved_next_key_in_cycle = (    
+                    _preserved_next_key_in_cycle = (
                         await _singleton_instance.get_next_key()
                     )
                 else:
@@ -427,9 +429,10 @@ async def reset_key_manager_instance():
                 logger.warning(
                     "Could not preserve next key hint: key cycle was empty or exhausted in old instance."
                 )
-                _preserved_next_key_in_cycle = None 
+                _preserved_next_key_in_cycle = None
             except Exception as e:
-                logger.error(f"Error preserving next key hint during reset: {e}")
+                logger.error(
+                    f"Error preserving next key hint during reset: {e}")
                 _preserved_next_key_in_cycle = None
 
             # 4. 保存 vertex_key_cycle 的下一个 key 提示
@@ -443,12 +446,12 @@ async def reset_key_manager_instance():
             except StopIteration:
                 logger.warning(
                     "Could not preserve next key hint: Vertex key cycle was empty or exhausted in old instance."
-                )   
+                )
                 _preserved_vertex_next_key_in_cycle = None
             except Exception as e:
-                logger.error(f"Error preserving next key hint during reset: {e}")
+                logger.error(
+                    f"Error preserving next key hint during reset: {e}")
                 _preserved_vertex_next_key_in_cycle = None
-                
 
             _singleton_instance = None
             logger.info(

app/service/stats/stats_service.py

@@ -1,6 +1,7 @@
 # app/service/stats_service.py
 
 import datetime
+from typing import Union
 
 from sqlalchemy import and_, case, func, or_, select
 
@@ -195,10 +196,11 @@ class StatsService:
             return details
 
         except Exception as e:
-            logger.error(f"Failed to get API call details for period '{period}': {e}")
+            logger.error(
+                f"Failed to get API call details for period '{period}': {e}")
             raise
 
-    async def get_key_usage_details_last_24h(self, key: str) -> dict | None:
+    async def get_key_usage_details_last_24h(self, key: str) -> Union[dict, None]:
         """
         获取指定 API 密钥在过去 24 小时内按模型统计的调用次数。
 
@@ -218,7 +220,8 @@ class StatsService:
         try:
             query = (
                 select(
-                    RequestLog.model_name, func.count(RequestLog.id).label("call_count")
+                    RequestLog.model_name, func.count(
+                        RequestLog.id).label("call_count")
                 )
                 .where(
                     RequestLog.api_key == key,
@@ -237,7 +240,8 @@ class StatsService:
                 )
                 return {}
 
-            usage_details = {row["model_name"]: row["call_count"] for row in results}
+            usage_details = {row["model_name"]: row["call_count"]
+                             for row in results}
             logger.info(
                 f"Successfully fetched usage details for key ending in ...{key[-4:]}: {usage_details}"
             )

app/service/tts/tts_service.py

@@ -0,0 +1,94 @@
+import datetime
+import io
+import re
+import time
+import wave
+from typing import Optional
+
+from google import genai
+
+from app.config.config import settings
+from app.database.services import add_error_log, add_request_log
+from app.domain.openai_models import TTSRequest
+from app.log.logger import get_openai_logger
+
+logger = get_openai_logger()
+
+
+def _create_wav_file(audio_data: bytes) -> bytes:
+    """Creates a WAV file in memory from raw audio data."""
+    with io.BytesIO() as wav_file:
+        with wave.open(wav_file, "wb") as wf:
+            wf.setnchannels(1)  # Mono
+            wf.setsampwidth(2)  # 16-bit
+            wf.setframerate(24000)  # 24kHz sample rate
+            wf.writeframes(audio_data)
+        return wav_file.getvalue()
+
+
+class TTSService:
+    async def create_tts(self, request: TTSRequest, api_key: str) -> Optional[bytes]:
+        """
+        使用 Google Gemini SDK 创建音频。
+        """
+        start_time = time.perf_counter()
+        request_datetime = datetime.datetime.now()
+        is_success = False
+        status_code = None
+        response = None
+        error_log_msg = ""
+        try:
+            client = genai.Client(api_key=api_key)
+            response =await client.aio.models.generate_content(
+                model=settings.TTS_MODEL,
+                contents=f"Speak in a {settings.TTS_SPEED} speed voice: {request.input}",
+                config={
+                    "response_modalities": ["Audio"],
+                    "speech_config": {
+                        "voice_config": {
+                            "prebuilt_voice_config": {
+                                "voice_name": settings.TTS_VOICE_NAME
+                            }
+                        }
+                    },
+                },
+            )
+            if (
+                response.candidates
+                and response.candidates[0].content.parts
+                and response.candidates[0].content.parts[0].inline_data
+            ):
+                raw_audio_data = response.candidates[0].content.parts[0].inline_data.data
+                is_success = True
+                status_code = 200
+                return _create_wav_file(raw_audio_data)
+        except Exception as e:
+            is_success = False
+            error_log_msg = f"Generic error: {e}"
+            logger.error(f"An error occurred in TTSService: {error_log_msg}")
+            match = re.search(r"status code (\d+)", str(e))
+            if match:
+                status_code = int(match.group(1))
+            else:
+                status_code = 500
+            raise
+        finally:
+            end_time = time.perf_counter()
+            latency_ms = int((end_time - start_time) * 1000)
+            if not is_success:
+                await add_error_log(
+                    gemini_key=api_key,
+                    model_name=settings.TTS_MODEL,
+                    error_type="google-tts",
+                    error_log=error_log_msg,
+                    error_code=status_code,
+                    request_msg=request.input
+                 )
+            await add_request_log(
+                model_name=settings.TTS_MODEL,
+                api_key=api_key,
+                is_success=is_success,
+                status_code=status_code,
+                latency_ms=latency_ms,
+                request_time=request_datetime
+            )

app/static/js/config_editor.js

@@ -12,7 +12,7 @@ const PROXY_REGEX =
   /(?:https?|socks5):\/\/(?:[^:@\/]+(?::[^@\/]+)?@)?(?:[^:\/\s]+)(?::\d+)?/g;
 const VERTEX_API_KEY_REGEX = /AQ\.[a-zA-Z0-9_]{50}/g; // 新增 Vertex API Key 正则
 const MASKED_VALUE = "••••••••";
- 
+
 // DOM Elements - Global Scope for frequently accessed elements
 const safetySettingsContainer = document.getElementById(
   "SAFETY_SETTINGS_container"
@@ -31,7 +31,7 @@ const bulkDeleteProxyModal = document.getElementById("bulkDeleteProxyModal");
 const bulkDeleteProxyInput = document.getElementById("bulkDeleteProxyInput");
 const resetConfirmModal = document.getElementById("resetConfirmModal");
 const configForm = document.getElementById("configForm"); // Added for frequent use
- 
+
 // Vertex API Key Modal Elements
 const vertexApiKeyModal = document.getElementById("vertexApiKeyModal");
 const vertexApiKeyBulkInput = document.getElementById("vertexApiKeyBulkInput");
@@ -41,7 +41,7 @@ const bulkDeleteVertexApiKeyModal = document.getElementById(
 const bulkDeleteVertexApiKeyInput = document.getElementById(
   "bulkDeleteVertexApiKeyInput"
 );
- 
+
 // Model Helper Modal Elements
 const modelHelperModal = document.getElementById("modelHelperModal");
 const modelHelperTitleElement = document.getElementById("modelHelperTitle");
@@ -384,7 +384,7 @@ document.addEventListener("DOMContentLoaded", function () {
   }
 
   initializeSensitiveFields(); // Initialize sensitive field handling
- 
+
   // Vertex API Key Modal Elements and Events
   const addVertexApiKeyBtn = document.getElementById("addVertexApiKeyBtn");
   const closeVertexApiKeyModalBtn = document.getElementById(
@@ -408,7 +408,7 @@ document.addEventListener("DOMContentLoaded", function () {
   const confirmBulkDeleteVertexApiKeyBtn = document.getElementById(
     "confirmBulkDeleteVertexApiKeyBtn"
   );
- 
+
   if (addVertexApiKeyBtn) {
     addVertexApiKeyBtn.addEventListener("click", () => {
       openModal(vertexApiKeyModal);
@@ -428,7 +428,7 @@ document.addEventListener("DOMContentLoaded", function () {
       "click",
       handleBulkAddVertexApiKeys
     );
- 
+
   if (bulkDeleteVertexApiKeyBtn) {
     bulkDeleteVertexApiKeyBtn.addEventListener("click", () => {
       openModal(bulkDeleteVertexApiKeyModal);
@@ -448,7 +448,7 @@ document.addEventListener("DOMContentLoaded", function () {
       "click",
       handleBulkDeleteVertexApiKeys
     );
- 
+
   // Model Helper Modal Event Listeners
   if (closeModelHelperModalBtn) {
     closeModelHelperModalBtn.addEventListener("click", () =>
@@ -765,7 +765,7 @@ async function initConfig() {
       FAKE_STREAM_EMPTY_DATA_INTERVAL_SECONDS: 5,
       // --- 结束：处理假流式配置的默认值 ---
     };
- 
+
     populateForm(defaultConfig);
     if (configForm) {
       // Ensure form exists
@@ -1177,7 +1177,7 @@ function handleBulkDeleteProxies() {
   }
   bulkDeleteProxyInput.value = "";
 }
- 
+
 /**
  * Handles the bulk addition of Vertex API keys from the modal input.
  */
@@ -1192,10 +1192,10 @@ function handleBulkAddVertexApiKeys() {
   ) {
     return;
   }
- 
+
   const bulkText = vertexApiKeyBulkInput.value;
   const extractedKeys = bulkText.match(VERTEX_API_KEY_REGEX) || [];
- 
+
   const currentKeyInputs = vertexApiKeyContainer.querySelectorAll(
     `.${ARRAY_INPUT_CLASS}.${SENSITIVE_INPUT_CLASS}`
   );
@@ -1206,16 +1206,16 @@ function handleBulkAddVertexApiKeys() {
         : input.value;
     })
     .filter((key) => key && key.trim() !== "" && key !== MASKED_VALUE);
- 
+
   const combinedKeys = new Set([...currentKeys, ...extractedKeys]);
   const uniqueKeys = Array.from(combinedKeys);
- 
+
   vertexApiKeyContainer.innerHTML = ""; // Clear existing items
- 
+
   uniqueKeys.forEach((key) => {
     addArrayItemWithValue("VERTEX_API_KEYS", key); // VERTEX_API_KEYS are sensitive
   });
- 
+
   // Ensure new sensitive inputs are masked
   const newKeyInputs = vertexApiKeyContainer.querySelectorAll(
     `.${ARRAY_INPUT_CLASS}.${SENSITIVE_INPUT_CLASS}`
@@ -1229,7 +1229,7 @@ function handleBulkAddVertexApiKeys() {
       input.dispatchEvent(focusoutEvent);
     }
   });
- 
+
   closeModal(vertexApiKeyModal);
   showNotification(
     `添加/更新了 ${uniqueKeys.length} 个唯一 Vertex 密钥`,
@@ -1237,7 +1237,7 @@ function handleBulkAddVertexApiKeys() {
   );
   vertexApiKeyBulkInput.value = "";
 }
- 
+
 /**
  * Handles the bulk deletion of Vertex API keys based on input from the modal.
  */
@@ -1252,15 +1252,15 @@ function handleBulkDeleteVertexApiKeys() {
   ) {
     return;
   }
- 
+
   const bulkText = bulkDeleteVertexApiKeyInput.value;
   if (!bulkText.trim()) {
     showNotification("请粘贴需要删除的 Vertex API 密钥", "warning");
     return;
   }
- 
+
   const keysToDelete = new Set(bulkText.match(VERTEX_API_KEY_REGEX) || []);
- 
+
   if (keysToDelete.size === 0) {
     showNotification(
       "未在输入内容中提取到有效的 Vertex API 密钥格式",
@@ -1268,10 +1268,10 @@ function handleBulkDeleteVertexApiKeys() {
     );
     return;
   }
- 
+
   const keyItems = vertexApiKeyContainer.querySelectorAll(`.${ARRAY_ITEM_CLASS}`);
   let deleteCount = 0;
- 
+
   keyItems.forEach((item) => {
     const input = item.querySelector(
       `.${ARRAY_INPUT_CLASS}.${SENSITIVE_INPUT_CLASS}`
@@ -1286,9 +1286,9 @@ function handleBulkDeleteVertexApiKeys() {
       deleteCount++;
     }
   });
- 
+
   closeModal(bulkDeleteVertexApiKeyModal);
- 
+
   if (deleteCount > 0) {
     showNotification(`成功删除了 ${deleteCount} 个匹配的 Vertex 密钥`, "success");
   } else {
@@ -1296,7 +1296,7 @@ function handleBulkDeleteVertexApiKeys() {
   }
   bulkDeleteVertexApiKeyInput.value = "";
 }
- 
+
 /**
  * Switches the active configuration tab.
  * @param {string} tabId - The ID of the tab to switch to.
@@ -1442,7 +1442,7 @@ function addArrayItemWithValue(key, value) {
   const isSensitive =
     key === "API_KEYS" || isAllowedToken || isVertexApiKey; // 更新敏感判断
   const modelId = isThinkingModel ? generateUUID() : null;
- 
+
   const arrayItem = document.createElement("div");
   arrayItem.className = `${ARRAY_ITEM_CLASS} flex items-center mb-2 gap-2`;
   if (isThinkingModel) {
@@ -1535,14 +1535,14 @@ function createAndAppendBudgetMapItem(mapKey, mapValue, modelId) {
   valueInput.value = isNaN(intValue) ? 0 : intValue;
   valueInput.placeholder = "预算 (整数)";
   valueInput.className = `${MAP_VALUE_INPUT_CLASS} w-24 px-3 py-2 border border-gray-300 rounded-md focus:outline-none focus:border-primary-500 focus:ring focus:ring-primary-200 focus:ring-opacity-50`;
-  valueInput.min = 0;
+  valueInput.min = -1;
-  valueInput.max = 24576;
+  valueInput.max = 32767;
   valueInput.addEventListener("input", function () {
-    let val = this.value.replace(/[^0-9]/g, "");
+    let val = this.value.replace(/[^0-9-]/g, "");
     if (val !== "") {
       val = parseInt(val, 10);
-      if (val < 0) val = 0;
+      if (val < -1) val = -1;
-      if (val > 24576) val = 24576;
+      if (val > 32767) val = 32767;
     }
     this.value = val; // Corrected variable name
   });

app/templates/config_editor.html

@@ -745,6 +745,13 @@ endblock %} {% block head_extra_styles %}
       >
         模型配置
       </button>
+      <button
+        class="tab-btn px-5 py-2 rounded-full font-medium text-sm transition-all duration-200"
+        data-tab="tts"
+        style="background-color: #f8fafc !important; color: #64748b !important; border: 2px solid #e2e8f0 !important; box-shadow: 0 1px 3px 0 rgba(0, 0, 0, 0.1) !important; font-weight: 500 !important;"
+      >
+        TTS 配置
+      </button>
       <button
         class="tab-btn px-5 py-2 rounded-full font-medium text-sm transition-all duration-200"
         data-tab="image"
@@ -935,7 +942,33 @@ endblock %} {% block head_extra_styles %}
           />
           <small class="text-gray-500 mt-1 block">Vertex Express API的基础URL</small>
         </div>
- 
+        <!-- 智能路由配置 -->
+        <div class="mb-6">
+          <div class="flex items-center justify-between">
+              <label
+                      for="URL_NORMALIZATION_ENABLED"
+                      class="font-semibold text-gray-700"
+              >启用智能路由映射</label
+              >
+              <div
+                      class="relative inline-block w-10 mr-2 align-middle select-none transition duration-200 ease-in"
+              >
+                  <input
+                          type="checkbox"
+                          name="URL_NORMALIZATION_ENABLED"
+                          id="URL_NORMALIZATION_ENABLED"
+                          class="toggle-checkbox absolute block w-6 h-6 rounded-full bg-white border-4 appearance-none cursor-pointer"
+                  />
+                  <label
+                          for="URL_NORMALIZATION_ENABLED"
+                          class="toggle-label block overflow-hidden h-6 rounded-full bg-gray-300 cursor-pointer"
+                  ></label>
+              </div>
+          </div>
+          <small class="text-gray-500 mt-1 block">
+            自动客户端请求的url拼接为正确格式（仅保证正常聊天，出现问题请关闭）
+          </small>
+        </div>
         <!-- 最大失败次数 -->
         <div class="mb-6">
           <label
@@ -1021,6 +1054,33 @@ endblock %} {% block head_extra_styles %}
             socks5://host:port。点击按钮可批量添加或删除。</small
           >
         </div>
+        <!-- 代理使用策略 -->
+        <div class="mb-6">
+          <div class="flex items-center justify-between">
+              <label
+                      for="PROXIES_USE_CONSISTENCY_HASH_BY_API_KEY"
+                      class="font-semibold text-gray-700"
+              >是否开启固定代理策略</label
+              >
+              <div
+                      class="relative inline-block w-10 mr-2 align-middle select-none transition duration-200 ease-in"
+              >
+                  <input
+                          type="checkbox"
+                          name="PROXIES_USE_CONSISTENCY_HASH_BY_API_KEY"
+                          id="PROXIES_USE_CONSISTENCY_HASH_BY_API_KEY"
+                          class="toggle-checkbox absolute block w-6 h-6 rounded-full bg-white border-4 appearance-none cursor-pointer"
+                  />
+                  <label
+                          for="PROXIES_USE_CONSISTENCY_HASH_BY_API_KEY"
+                          class="toggle-label block overflow-hidden h-6 rounded-full bg-gray-300 cursor-pointer"
+                  ></label>
+              </div>
+          </div>
+          <small class="text-gray-500 mt-1 block"
+          >开启后，对于每一个API_KEY将根据算法从代理列表中选取同一个代理IP，防止一个API_KEY同时被多个IP访问，也同时防止了一个IP访问了过多的API_KEY。</small
+          >
+        </div>
       </div>
 
       <!-- 模型相关配置 -->
@@ -1272,7 +1332,7 @@ endblock %} {% block head_extra_styles %}
                         </div> -->
           <small class="text-gray-500 mt-1 block"
             >为每个思考模型设置预算（整数，最大值
-            24576），此项与上方模型列表自动关联。</small
+            32767），此项与上方模型列表自动关联。</small
           >
         </div>
         <!-- 安全设置 -->
@@ -1317,11 +1377,97 @@ endblock %} {% block head_extra_styles %}
           </div>
         </div>
       </div>
-
+ 
-      <!-- 图像生成相关配置 -->
+       <!-- TTS配置 -->
-      <div class="config-section" id="image-section">
+      <div class="config-section" id="tts-section">
         <h2
           class="text-xl font-bold mb-6 pb-3 border-b flex items-center gap-2 text-gray-800 border-violet-300 border-opacity-30"
+        >
+          <i class="fas fa-volume-up text-violet-400"></i> TTS 相关配置
+        </h2>
+
+        <!-- TTS 模型 -->
+        <div class="mb-6">
+          <label for="TTS_MODEL" class="block font-semibold mb-2 text-gray-700"
+            >TTS 模型</label
+          >
+          <select
+            id="TTS_MODEL"
+            name="TTS_MODEL"
+            class="w-full px-4 py-3 rounded-lg form-select-themed"
+          >
+            <option value="gemini-2.5-flash-preview-tts">gemini-2.5-flash-preview-tts</option>
+            <option value="gemini-2.5-pro-preview-tts">gemini-2.5-pro-preview-tts</option>
+          </select>
+          <small class="text-gray-500 mt-1 block">用于TTS的模型</small>
+        </div>
+
+        <!-- TTS 语音名称 -->
+        <div class="mb-6">
+          <label for="TTS_VOICE_NAME" class="block font-semibold mb-2 text-gray-700"
+            >TTS 语音名称</label
+          >
+          <select
+            id="TTS_VOICE_NAME"
+            name="TTS_VOICE_NAME"
+            class="w-full px-4 py-3 rounded-lg form-select-themed"
+          >
+            <option value="Zephyr">Zephyr (明亮)</option>
+            <option value="Puck">Puck (欢快)</option>
+            <option value="Charon">Charon (信息丰富)</option>
+            <option value="Kore">Kore (坚定)</option>
+            <option value="Fenrir">Fenrir (易激动)</option>
+            <option value="Leda">Leda (年轻)</option>
+            <option value="Orus">Orus (坚定)</option>
+            <option value="Aoede">Aoede (轻松)</option>
+            <option value="Callirhoe">Callirhoe (随和)</option>
+            <option value="Autonoe">Autonoe (明亮)</option>
+            <option value="Enceladus">Enceladus (呼吸感)</option>
+            <option value="Iapetus">Iapetus (清晰)</option>
+            <option value="Umbriel">Umbriel (随和)</option>
+            <option value="Algieba">Algieba (平滑)</option>
+            <option value="Despina">Despina (平滑)</option>
+            <option value="Erinome">Erinome (清晰)</option>
+            <option value="Algenib">Algenib (沙哑)</option>
+            <option value="Rasalgethi">Rasalgethi (信息丰富)</option>
+            <option value="Laomedeia">Laomedeia (欢快)</option>
+            <option value="Achernar">Achernar (轻柔)</option>
+            <option value="Alnilam">Alnilam (坚定)</option>
+            <option value="Schedar">Schedar (平稳)</option>
+            <option value="Gacrux">Gacrux (成熟)</option>
+            <option value="Pulcherrima">Pulcherrima (向前)</option>
+            <option value="Achird">Achird (友好)</option>
+            <option value="Zubenelgenubi">Zubenelgenubi (休闲)</option>
+            <option value="Vindemiatrix">Vindemiatrix (温柔)</option>
+            <option value="Sadachbia">Sadachbia (活泼)</option>
+            <option value="Sadaltager">Sadaltager (博学)</option>
+            <option value="Sulafat">Sulafat (温暖)</option>
+          </select>
+          <small class="text-gray-500 mt-1 block">TTS 的语音名称，控制风格、语调、口音和节奏</small>
+        </div>
+
+        <!-- TTS 语速 -->
+        <div class="mb-6">
+          <label for="TTS_SPEED" class="block font-semibold mb-2 text-gray-700"
+            >TTS 语速</label
+          >
+          <select
+            id="TTS_SPEED"
+            name="TTS_SPEED"
+            class="w-full px-4 py-3 rounded-lg form-select-themed"
+          >
+            <option value="slow">慢</option>
+            <option value="normal">正常</option>
+            <option value="fast">快</option>
+          </select>
+          <small class="text-gray-500 mt-1 block">选择 TTS 的语速</small>
+        </div>
+      </div>
+
+       <!-- 图像生成相关配置 -->
+       <div class="config-section" id="image-section">
+         <h2
+          class="text-xl font-bold mb-6 pb-3 border-b flex items-center gap-2 text-gray-800 border-violet-300 border-opacity-30"
         >
           <i class="fas fa-image text-violet-400"></i> 图像生成配置
         </h2>
@@ -1456,14 +1602,31 @@ endblock %} {% block head_extra_styles %}
           />
           <small class="text-gray-500 mt-1 block">Cloudflare图床的认证码</small>
         </div>
+
+        <!-- Cloudflare上传文件夹 -->
+        <div class="mb-6 provider-config" data-provider="cloudflare_imgbed">
+          <label
+            for="CLOUDFLARE_IMGBED_UPLOAD_FOLDER"
+            class="block font-semibold mb-2 text-gray-700"
+            >Cloudflare上传文件夹</label
+          >
+          <input
+            type="text"
+            id="CLOUDFLARE_IMGBED_UPLOAD_FOLDER"
+            name="CLOUDFLARE_IMGBED_UPLOAD_FOLDER"
+            placeholder=""
+            class="w-full px-4 py-3 rounded-lg form-input-themed"
+          />
+          <small class="text-gray-500 mt-1 block">Cloudflare图床的上传文件夹路径（可选）</small>
+        </div>
       </div>
 
-      <!-- 流式输出优化器配置 -->
+      <!-- 流式输出优化配置 -->
       <div class="config-section" id="stream-section">
         <h2
           class="text-xl font-bold mb-6 pb-3 border-b flex items-center gap-2 text-gray-800 border-violet-300 border-opacity-30"
         >
-          <i class="fas fa-stream text-violet-400"></i> 流式输出优化器
+          <i class="fas fa-stream text-violet-400"></i> 流式输出相关配置
         </h2>
 
         <!-- 启用流式输出优化 -->
@@ -2328,7 +2491,7 @@ endblock %} {% block head_extra_styles %}
         let val = this.value.replace(/[^0-9]/g, "");
         if (val !== "") {
           val = parseInt(val, 10);
-          if (val > 24576) val = 24576;
+          if (val > 32767) val = 32767;
         }
         this.value = val;
 

app/utils/uploader.py

@@ -261,18 +261,20 @@ class PicGoUploader(ImageUploader):
 
 class CloudFlareImgBedUploader(ImageUploader):
     """CloudFlare图床上传器"""
-    
+
-    def __init__(self, auth_code: str, api_url: str):
+    def __init__(self, auth_code: str, api_url: str, upload_folder: str = ""):
         """
         初始化CloudFlare图床上传器
         
         Args:
             auth_code: 认证码
             api_url: 上传API地址
+            upload_folder: 上传文件夹路径（可选）
         """
         self.auth_code = auth_code
         self.api_url = api_url
-        
+        self.upload_folder = upload_folder
+
     def upload(self, file: bytes, filename: str) -> UploadResponse:
         """
         上传图片到CloudFlare图床
@@ -288,12 +290,16 @@ class CloudFlareImgBedUploader(ImageUploader):
             UploadError: 上传失败时抛出异常
         """
         try:
-            # 准备请求URL（添加认证码参数，如果存在）
+            # 准备请求URL参数
+            params = []
+            if self.upload_folder:
+                params.append(f"uploadFolder={self.upload_folder}")
             if self.auth_code:
-                request_url = f"{self.api_url}?authCode={self.auth_code}&uploadNameType=origin"
+                params.append(f"authCode={self.auth_code}")
-            else:
+            params.append("uploadNameType=origin")
-                request_url = f"{self.api_url}?uploadNameType=origin"
+
-            
+            request_url = f"{self.api_url}?{'&'.join(params)}"
+
             # 准备文件数据
             files = {
                 "file": (filename, file)
@@ -388,6 +394,7 @@ class ImageUploaderFactory:
         elif provider == "cloudflare_imgbed":
             return CloudFlareImgBedUploader(
                 credentials["auth_code"],
-                credentials["base_url"]
+                credentials["base_url"],
+                credentials.get("upload_folder", ""),
             )
         raise ValueError(f"Unknown provider: {provider}")

files/dataocean.svg

@@ -0,0 +1,71 @@
+<?xml version="1.0" encoding="utf-8"?>
+<!-- Generator: Adobe Illustrator 19.0.0, SVG Export Plug-In . SVG Version: 6.00 Build 0)  -->
+<svg version="1.1" id="Layer_1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" x="0px" y="0px"
+	 viewBox="0 0 603 103" style="enable-background:new 0 0 603 103;" xml:space="preserve">
+<style type="text/css">
+	.st0{fill:#0080FF;}
+	.st1{fill-rule:evenodd;clip-rule:evenodd;fill:#0080FF;}
+</style>
+<g id="XMLID_2369_">
+	<g id="XMLID_2638_">
+		<g id="XMLID_2639_">
+			<g>
+				<g id="XMLID_44_">
+					<g id="XMLID_48_">
+						<path id="XMLID_49_" class="st0" d="M52.1,102.1l0-19.6c20.8,0,36.8-20.6,28.9-42.4C78,32,71.6,25.5,63.5,22.6
+							c-21.8-7.9-42.4,8.1-42.4,28.9c0,0,0,0,0,0l-19.6,0c0-33.1,32-58.9,66.7-48.1c15.2,4.7,27.2,16.8,31.9,31.9
+							C110.9,70.1,85.2,102.1,52.1,102.1z"/>
+					</g>
+					<polygon id="XMLID_47_" class="st1" points="52.1,82.5 32.6,82.5 32.6,63 32.6,63 52.1,63 52.1,63 					"/>
+					<polygon id="XMLID_46_" class="st1" points="32.6,97.5 17.6,97.5 17.6,97.5 17.6,82.5 32.6,82.5 32.6,97.5 					"/>
+					<polygon id="XMLID_45_" class="st1" points="17.6,82.5 5,82.5 5,82.5 5,70 5,70 17.6,70 17.6,70 					"/>
+				</g>
+			</g>
+		</g>
+	</g>
+	<g id="XMLID_2370_">
+		<path id="XMLID_2635_" class="st0" d="M181.5,30.2c-5.8-4-13-6.1-21.4-6.1h-18.3v58.1h18.3c8.4,0,15.6-2.1,21.4-6.4
+			c3.2-2.2,5.7-5.4,7.4-9.3c1.7-3.9,2.6-8.5,2.6-13.7c0-5.1-0.9-9.7-2.6-13.6C187.2,35.4,184.7,32.3,181.5,30.2z M152.5,34h5.8
+			c6.4,0,11.7,1.3,15.7,3.7c4.4,2.7,6.7,7.8,6.7,15.1c0,7.6-2.3,12.9-6.7,15.8h0c-3.8,2.5-9.1,3.8-15.6,3.8h-5.8V34z"/>
+		<path id="XMLID_2634_" class="st0" d="M204.3,23.4c-1.8,0-3.3,0.6-4.5,1.8c-1.2,1.2-1.9,2.7-1.9,4.4c0,1.8,0.6,3.3,1.9,4.5
+			c1.2,1.2,2.7,1.9,4.5,1.9c1.8,0,3.3-0.6,4.5-1.9c1.2-1.2,1.9-2.8,1.9-4.5c0-1.8-0.6-3.3-1.9-4.4C207.6,24,206,23.4,204.3,23.4z"/>
+		<rect id="XMLID_2564_" x="199" y="41.3" class="st0" width="10.3" height="41"/>
+		<path id="XMLID_2561_" class="st0" d="M246.8,44.7c-3.1-2.8-6.6-4.4-10.3-4.4c-5.7,0-10.4,2-14.1,5.8c-3.7,3.8-5.5,8.8-5.5,14.7
+			c0,5.8,1.8,10.7,5.5,14.7c3.7,3.8,8.4,5.8,14.1,5.8c4,0,7.4-1.1,10.2-3.3V79c0,3.4-0.9,6-2.7,7.9c-1.8,1.8-4.3,2.7-7.4,2.7
+			c-4.8,0-7.7-1.9-11.4-6.8l-7,6.7l0.2,0.3c1.5,2.1,3.8,4.2,6.9,6.2c3.1,2,6.9,3,11.5,3c6.1,0,11.1-1.9,14.7-5.6
+			c3.7-3.7,5.5-8.7,5.5-14.9V41.3h-10.1V44.7z M244.1,68.9c-1.8,2-4.1,3-7.1,3c-3,0-5.3-1-7-3c-1.8-2-2.7-4.7-2.7-8
+			c0-3.3,0.9-6.1,2.7-8.1c1.8-2,4.1-3.1,7-3.1c3,0,5.3,1,7.1,3.1c1.8,2,2.7,4.8,2.7,8.1C246.8,64.2,245.8,66.9,244.1,68.9z"/>
+		<rect id="XMLID_2560_" x="265.7" y="41.3" class="st0" width="10.3" height="41"/>
+		<path id="XMLID_2552_" class="st0" d="M271,23.4c-1.8,0-3.3,0.6-4.5,1.8c-1.2,1.2-1.9,2.7-1.9,4.4c0,1.8,0.6,3.3,1.9,4.5
+			c1.2,1.2,2.7,1.9,4.5,1.9c1.8,0,3.3-0.6,4.5-1.9c1.2-1.2,1.9-2.8,1.9-4.5c0-1.8-0.6-3.3-1.9-4.4C274.3,24,272.7,23.4,271,23.4z"/>
+		<path id="XMLID_2509_" class="st0" d="M298.6,30.3h-10.1v11.1h-5.9v9.4h5.9v17c0,5.3,1.1,9.1,3.2,11.3c2.1,2.2,5.8,3.3,11.1,3.3
+			c1.7,0,3.4-0.1,5-0.2l0.5,0v-9.4l-3.5,0.2c-2.5,0-4.1-0.4-4.9-1.3c-0.8-0.9-1.2-2.7-1.2-5.4V50.7h9.6v-9.4h-9.6V30.3z"/>
+		<rect id="XMLID_2508_" x="356.5" y="24.1" class="st0" width="10.3" height="58.1"/>
+		<path id="XMLID_2470_" class="st0" d="M470.9,67.6c-1.8,2.1-3.7,3.9-5.2,4.8v0c-1.4,0.9-3.2,1.4-5.3,1.4c-3,0-5.5-1.1-7.5-3.4
+			c-2-2.3-3-5.2-3-8.7s1-6.4,2.9-8.6c2-2.3,4.4-3.4,7.4-3.4c3.3,0,6.8,2.1,9.8,5.6l6.8-6.5l0,0c-4.4-5.8-10.1-8.5-16.9-8.5
+			c-5.7,0-10.6,2.1-14.6,6.1c-4,4-6,9.2-6,15.3s2,11.2,6,15.3c4,4.1,8.9,6.1,14.6,6.1c7.5,0,13.5-3.2,17.5-9.1L470.9,67.6z"/>
+		<path id="XMLID_2460_" class="st0" d="M513.2,47c-1.5-2-3.5-3.7-5.9-4.9c-2.5-1.2-5.3-1.8-8.5-1.8c-5.8,0-10.5,2.1-14,6.3
+			c-3.4,4.2-5.2,9.3-5.2,15.4c0,6.2,1.9,11.3,5.7,15.3c3.7,3.9,8.8,5.9,14.9,5.9c6.9,0,12.7-2.8,16.9-8.4l0.2-0.3l-6.7-6.5l0,0
+			c-0.6,0.8-1.5,1.6-2.3,2.4c-1,1-2,1.7-3,2.2c-1.5,0.8-3.3,1.1-5.2,1.1c-2.9,0-5.2-0.8-7-2.5c-1.7-1.5-2.7-3.6-2.9-6.2h27.3
+			l0.1-3.8c0-2.7-0.4-5.2-1.1-7.6C515.8,51.3,514.7,49.1,513.2,47z M490.7,56.7c0.5-2,1.4-3.6,2.7-4.9c1.4-1.4,3.2-2.1,5.4-2.1
+			c2.5,0,4.4,0.7,5.7,2.1c1.2,1.3,1.9,2.9,2.1,4.8H490.7z"/>
+		<path id="XMLID_2456_" class="st0" d="M552.8,44.4L552.8,44.4c-3.1-2.7-7.4-4-12.8-4c-3.4,0-6.6,0.8-9.5,2.2
+			c-2.7,1.4-5.3,3.6-7,6.6l0.1,0.1l6.6,6.3c2.7-4.3,5.7-5.8,9.7-5.8c2.2,0,3.9,0.6,5.3,1.7c1.4,1.1,2,2.6,2,4.4v2
+			c-2.6-0.8-5.1-1.2-7.6-1.2c-5.1,0-9.3,1.2-12.4,3.6c-3.1,2.4-4.7,5.9-4.7,10.2c0,3.8,1.3,7,4,9.3c2.7,2.2,6,3.4,9.9,3.4
+			c3.9,0,7.6-1.6,10.9-4.3v3.4h10.1V55.9C557.6,51,556,47.1,552.8,44.4z M534.5,66.6c1.2-0.8,2.8-1.2,4.9-1.2c2.5,0,5.1,0.5,7.8,1.5
+			v4C545,73,542,74,538.3,74c-1.8,0-3.2-0.4-4.1-1.2c-0.9-0.8-1.4-1.7-1.4-3C532.8,68.5,533.4,67.4,534.5,66.6z"/>
+		<path id="XMLID_2454_" class="st0" d="M597.2,45.2c-2.9-3.2-6.9-4.8-12-4.8c-4.1,0-7.4,1.2-9.9,3.5v-2.5h-10.1v41h10.3V59.7
+			c0-3.1,0.7-5.6,2.2-7.3c1.5-1.8,3.4-2.6,6.1-2.6c2.3,0,4.1,0.8,5.4,2.3c1.3,1.6,2,3.7,2,6.4v23.7h10.3V58.5
+			C601.5,52.9,600.1,48.4,597.2,45.2z"/>
+		<path id="XMLID_2450_" class="st0" d="M343.6,44.4L343.6,44.4c-3.1-2.7-7.4-4-12.8-4c-3.4,0-6.6,0.8-9.5,2.2
+			c-2.7,1.4-5.3,3.6-7,6.6l0.1,0.1l6.6,6.3c2.7-4.3,5.7-5.8,9.7-5.8c2.2,0,3.9,0.6,5.3,1.7c1.4,1.1,2,2.6,2,4.4v2
+			c-2.6-0.8-5.1-1.2-7.6-1.2c-5.1,0-9.3,1.2-12.4,3.6c-3.1,2.4-4.7,5.9-4.7,10.2c0,3.8,1.3,7,4,9.3c2.7,2.2,6,3.4,9.9,3.4
+			c3.9,0,7.6-1.6,10.9-4.3v3.4h10.1V55.9C348.3,51,346.7,47.1,343.6,44.4z M325.3,66.6c1.2-0.8,2.8-1.2,4.9-1.2
+			c2.5,0,5.1,0.5,7.8,1.5v4c-2.2,2.1-5.2,3.1-8.9,3.1c-1.8,0-3.2-0.4-4.1-1.2c-0.9-0.8-1.4-1.7-1.4-3
+			C323.6,68.5,324.1,67.4,325.3,66.6z"/>
+		<path id="XMLID_2371_" class="st0" d="M404.2,83.1c-16.5,0-30-13.4-30-30s13.4-30,30-30c16.5,0,30,13.4,30,30
+			S420.7,83.1,404.2,83.1z M404.2,33.8c-10.7,0-19.4,8.7-19.4,19.4s8.7,19.4,19.4,19.4c10.7,0,19.4-8.7,19.4-19.4
+			S414.9,33.8,404.2,33.8z"/>
+	</g>
+</g>
+</svg>