@musistudio/claude-code-router 1.0.27 → 1.0.29

package/README.md

@@ -8,12 +8,12 @@
 
 ## ✨ Features
 
--   **Model Routing**: Route requests to different models based on your needs (e.g., background tasks, thinking, long context).
--   **Multi-Provider Support**: Supports various model providers like OpenRouter, DeepSeek, Ollama, Gemini, Volcengine, and SiliconFlow.
--   **Request/Response Transformation**: Customize requests and responses for different providers using transformers.
--   **Dynamic Model Switching**: Switch models on-the-fly within Claude Code using the `/model` command.
--   **GitHub Actions Integration**: Trigger Claude Code tasks in your GitHub workflows.
--   **Plugin System**: Extend functionality with custom transformers.
+- **Model Routing**: Route requests to different models based on your needs (e.g., background tasks, thinking, long context).
+- **Multi-Provider Support**: Supports various model providers like OpenRouter, DeepSeek, Ollama, Gemini, Volcengine, and SiliconFlow.
+- **Request/Response Transformation**: Customize requests and responses for different providers using transformers.
+- **Dynamic Model Switching**: Switch models on-the-fly within Claude Code using the `/model` command.
+- **GitHub Actions Integration**: Trigger Claude Code tasks in your GitHub workflows.
+- **Plugin System**: Extend functionality with custom transformers.
 
 ## 🚀 Getting Started
 
@@ -36,6 +36,7 @@ npm install -g @musistudio/claude-code-router
 Create and configure your `~/.claude-code-router/config.json` file. For more details, you can refer to `config.example.json`.
 
 The `config.json` file has several key sections:
+
 - **`PROXY_URL`** (optional): You can set a proxy for API requests, for example: `"PROXY_URL": "http://127.0.0.1:7890"`.
 - **`LOG`** (optional): You can enable logging by setting it to `true`. The log file will be located at `$HOME/.claude-code-router.log`.
 - **`APIKEY`** (optional): You can set a secret key to authenticate requests. When set, clients must provide this key in the `Authorization` header (e.g., `Bearer your-secret-key`) or the `x-api-key` header. Example: `"APIKEY": "your-secret-key"`.
@@ -43,6 +44,7 @@ The `config.json` file has several key sections:
 
 - **`Providers`**: Used to configure different model providers.
 - **`Router`**: Used to set up routing rules. `default` specifies the default model, which will be used for all requests if no other route is configured.
+- **`API_TIMEOUT_MS`**: Specifies the timeout for API calls in milliseconds.
 
 Here is a comprehensive example:
 
@@ -51,6 +53,7 @@ Here is a comprehensive example:
   "APIKEY": "your-secret-key",
   "PROXY_URL": "http://127.0.0.1:7890",
   "LOG": true,
+  "API_TIMEOUT_MS": 600000,
   "Providers": [
     {
       "name": "openrouter",
@@ -106,16 +109,20 @@ Here is a comprehensive example:
       "name": "modelscope",
       "api_base_url": "https://api-inference.modelscope.cn/v1/chat/completions",
       "api_key": "",
-      "models": ["Qwen/Qwen3-Coder-480B-A35B-Instruct"],
+      "models": ["Qwen/Qwen3-Coder-480B-A35B-Instruct", "Qwen/Qwen3-235B-A22B-Thinking-2507"],
       "transformer": {
         "use": [
           [
             "maxtoken",
             {
-              "max_tokens": 8192
+              "max_tokens": 65536
             }
-          ]
-        ]
+          ],
+          "enhancetool"
+        ],
+        "Qwen/Qwen3-235B-A22B-Thinking-2507": {
+          "use": ["reasoning"]
+        }
       }
     },
     {
@@ -128,9 +135,10 @@ Here is a comprehensive example:
           [
             "maxtoken",
             {
-              "max_tokens": 8192
+              "max_tokens": 65536
             }
-          ]
+          ],
+          "enhancetool"
         ]
       }
     }
@@ -140,12 +148,12 @@ Here is a comprehensive example:
     "background": "ollama,qwen2.5-coder:latest",
     "think": "deepseek,deepseek-reasoner",
     "longContext": "openrouter,google/gemini-2.5-pro-preview",
+    "longContextThreshold": 60000,
     "webSearch": "gemini,gemini-2.5-flash"
   }
 }
 ```
 
-
 ### 3. Running Claude Code with the Router
 
 Start Claude Code using the router:
@@ -155,81 +163,93 @@ ccr code
 ```
 
 > **Note**: After modifying the configuration file, you need to restart the service for the changes to take effect:
+>
 > ```shell
 > ccr restart
 > ```
 
+### 4. UI Mode
+
+For a more intuitive experience, you can use the UI mode to manage your configuration:
+
+```shell
+ccr ui
+```
+
+This will open a web-based interface where you can easily view and edit your `config.json` file.
+
 #### Providers
 
 The `Providers` array is where you define the different model providers you want to use. Each provider object requires:
 
--   `name`: A unique name for the provider.
--   `api_base_url`: The full API endpoint for chat completions.
--   `api_key`: Your API key for the provider.
--   `models`: A list of model names available from this provider.
--   `transformer` (optional): Specifies transformers to process requests and responses.
+- `name`: A unique name for the provider.
+- `api_base_url`: The full API endpoint for chat completions.
+- `api_key`: Your API key for the provider.
+- `models`: A list of model names available from this provider.
+- `transformer` (optional): Specifies transformers to process requests and responses.
 
 #### Transformers
 
 Transformers allow you to modify the request and response payloads to ensure compatibility with different provider APIs.
 
--   **Global Transformer**: Apply a transformer to all models from a provider. In this example, the `openrouter` transformer is applied to all models under the `openrouter` provider.
-    ```json
-     {
-       "name": "openrouter",
-       "api_base_url": "https://openrouter.ai/api/v1/chat/completions",
-       "api_key": "sk-xxx",
-       "models": [
-         "google/gemini-2.5-pro-preview",
-         "anthropic/claude-sonnet-4",
-         "anthropic/claude-3.5-sonnet"
-       ],
-       "transformer": { "use": ["openrouter"] }
-     }
-    ```
--   **Model-Specific Transformer**: Apply a transformer to a specific model. In this example, the `deepseek` transformer is applied to all models, and an additional `tooluse` transformer is applied only to the `deepseek-chat` model.
-    ```json
-     {
-       "name": "deepseek",
-       "api_base_url": "https://api.deepseek.com/chat/completions",
-       "api_key": "sk-xxx",
-       "models": ["deepseek-chat", "deepseek-reasoner"],
-       "transformer": {
-         "use": ["deepseek"],
-         "deepseek-chat": { "use": ["tooluse"] }
-       }
-     }
-    ```
-
--   **Passing Options to a Transformer**: Some transformers, like `maxtoken`, accept options. To pass options, use a nested array where the first element is the transformer name and the second is an options object.
-    ```json
-    {
-      "name": "siliconflow",
-      "api_base_url": "https://api.siliconflow.cn/v1/chat/completions",
-      "api_key": "sk-xxx",
-      "models": ["moonshotai/Kimi-K2-Instruct"],
-      "transformer": {
-        "use": [
-          [
-            "maxtoken",
-            {
-              "max_tokens": 16384
-            }
-          ]
+- **Global Transformer**: Apply a transformer to all models from a provider. In this example, the `openrouter` transformer is applied to all models under the `openrouter` provider.
+  ```json
+  {
+    "name": "openrouter",
+    "api_base_url": "https://openrouter.ai/api/v1/chat/completions",
+    "api_key": "sk-xxx",
+    "models": [
+      "google/gemini-2.5-pro-preview",
+      "anthropic/claude-sonnet-4",
+      "anthropic/claude-3.5-sonnet"
+    ],
+    "transformer": { "use": ["openrouter"] }
+  }
+  ```
+- **Model-Specific Transformer**: Apply a transformer to a specific model. In this example, the `deepseek` transformer is applied to all models, and an additional `tooluse` transformer is applied only to the `deepseek-chat` model.
+
+  ```json
+  {
+    "name": "deepseek",
+    "api_base_url": "https://api.deepseek.com/chat/completions",
+    "api_key": "sk-xxx",
+    "models": ["deepseek-chat", "deepseek-reasoner"],
+    "transformer": {
+      "use": ["deepseek"],
+      "deepseek-chat": { "use": ["tooluse"] }
+    }
+  }
+  ```
+
+- **Passing Options to a Transformer**: Some transformers, like `maxtoken`, accept options. To pass options, use a nested array where the first element is the transformer name and the second is an options object.
+  ```json
+  {
+    "name": "siliconflow",
+    "api_base_url": "https://api.siliconflow.cn/v1/chat/completions",
+    "api_key": "sk-xxx",
+    "models": ["moonshotai/Kimi-K2-Instruct"],
+    "transformer": {
+      "use": [
+        [
+          "maxtoken",
+          {
+            "max_tokens": 16384
+          }
         ]
-      }
+      ]
     }
-    ```
+  }
+  ```
 
 **Available Built-in Transformers:**
 
--   `deepseek`: Adapts requests/responses for DeepSeek API.
--   `gemini`: Adapts requests/responses for Gemini API.
--   `openrouter`: Adapts requests/responses for OpenRouter API.
--   `groq`: Adapts requests/responses for groq API.
--   `maxtoken`: Sets a specific `max_tokens` value.
--   `tooluse`: Optimizes tool usage for certain models via `tool_choice`.
--   `gemini-cli` (experimental): Unofficial support for Gemini via Gemini CLI [gemini-cli.js](https://gist.github.com/musistudio/1c13a65f35916a7ab690649d3df8d1cd).
+- `deepseek`: Adapts requests/responses for DeepSeek API.
+- `gemini`: Adapts requests/responses for Gemini API.
+- `openrouter`: Adapts requests/responses for OpenRouter API.
+- `groq`: Adapts requests/responses for groq API.
+- `maxtoken`: Sets a specific `max_tokens` value.
+- `tooluse`: Optimizes tool usage for certain models via `tool_choice`.
+- `gemini-cli` (experimental): Unofficial support for Gemini via Gemini CLI [gemini-cli.js](https://gist.github.com/musistudio/1c13a65f35916a7ab690649d3df8d1cd).
 
 **Custom Transformers:**
 
@@ -238,12 +258,12 @@ You can also create your own transformers and load them via the `transformers` f
 ```json
 {
   "transformers": [
-      {
-        "path": "$HOME/.claude-code-router/plugins/gemini-cli.js",
-        "options": {
-          "project": "xxx"
-        }
+    {
+      "path": "$HOME/.claude-code-router/plugins/gemini-cli.js",
+      "options": {
+        "project": "xxx"
       }
+    }
   ]
 }
 ```
@@ -252,12 +272,12 @@ You can also create your own transformers and load them via the `transformers` f
 
 The `Router` object defines which model to use for different scenarios:
 
--   `default`: The default model for general tasks.
--   `background`: A model for background tasks. This can be a smaller, local model to save costs.
--   `think`: A model for reasoning-heavy tasks, like Plan Mode.
--   `longContext`: A model for handling long contexts (e.g., > 60K tokens).
--   `webSearch`: Used for handling web search tasks and this requires the model itself to support the feature. If you're using openrouter, you need to add the `:online` suffix after the model name.
-
+- `default`: The default model for general tasks.
+- `background`: A model for background tasks. This can be a smaller, local model to save costs.
+- `think`: A model for reasoning-heavy tasks, like Plan Mode.
+- `longContext`: A model for handling long contexts (e.g., > 60K tokens).
+- `longContextThreshold` (optional): The token count threshold for triggering the long context model. Defaults to 60000 if not specified.
+- `webSearch`: Used for handling web search tasks and this requires the model itself to support the feature. If you're using openrouter, you need to add the `:online` suffix after the model name.
 
 You can also switch models dynamically in Claude Code with the `/model` command:
 `/model provider_name,model_name`
@@ -290,11 +310,11 @@ Here is an example of a `custom-router.js` based on `custom-router.example.js`:
  * @returns {Promise<string|null>} - A promise that resolves to the "provider,model_name" string, or null to use the default router.
  */
 module.exports = async function router(req, config) {
-  const userMessage = req.body.messages.find(m => m.role === 'user')?.content;
+  const userMessage = req.body.messages.find((m) => m.role === "user")?.content;
 
-  if (userMessage && userMessage.includes('explain this code')) {
+  if (userMessage && userMessage.includes("explain this code")) {
     // Use a powerful model for code explanation
-    return 'openrouter,anthropic/claude-3.5-sonnet';
+    return "openrouter,anthropic/claude-3.5-sonnet";
   }
 
   // Fallback to the default router configuration
@@ -302,7 +322,6 @@ module.exports = async function router(req, config) {
 };
 ```
 
-
 ## 🤖 GitHub Actions
 
 Integrate Claude Code Router into your CI/CD pipeline. After setting up [Claude Code Actions](https://docs.anthropic.com/en/docs/claude-code/github-actions), modify your `.github/workflows/claude.yaml` to use the router:
@@ -364,8 +383,8 @@ This setup allows for interesting automations, like running tasks during off-pea
 
 ## 📝 Further Reading
 
--   [Project Motivation and How It Works](blog/en/project-motivation-and-how-it-works.md)
--   [Maybe We Can Do More with the Router](blog/en/maybe-we-can-do-more-with-the-route.md)
+- [Project Motivation and How It Works](blog/en/project-motivation-and-how-it-works.md)
+- [Maybe We Can Do More with the Router](blog/en/maybe-we-can-do-more-with-the-route.md)
 
 ## ❤️ Support & Sponsoring
 
@@ -387,39 +406,39 @@ A huge thank you to all our sponsors for their generous support!
 - @Simon Leischnig
 - [@duanshuaimin](https://github.com/duanshuaimin)
 - [@vrgitadmin](https://github.com/vrgitadmin)
-- @*o
+- @\*o
 - [@ceilwoo](https://github.com/ceilwoo)
-- @*说
-- @*更
-- @K*g
-- @R*R
+- @\*说
+- @\*更
+- @K\*g
+- @R\*R
 - [@bobleer](https://github.com/bobleer)
-- @*苗
-- @*划
+- @\*苗
+- @\*划
 - [@Clarence-pan](https://github.com/Clarence-pan)
 - [@carter003](https://github.com/carter003)
-- @S*r
-- @*晖
-- @*敏
-- @Z*z
-- @*然
+- @S\*r
+- @\*晖
+- @\*敏
+- @Z\*z
+- @\*然
 - [@cluic](https://github.com/cluic)
-- @*苗
+- @\*苗
 - [@PromptExpert](https://github.com/PromptExpert)
-- @*应
+- @\*应
 - [@yusnake](https://github.com/yusnake)
-- @*飞
-- @董*
-- @*汀
-- @*涯
-- @*:-）
-- @**磊   
-- @*琢
-- @*成
-- @Z*o
-- @*琨
+- @\*飞
+- @董\*
+- @\*汀
+- @\*涯
+- @\*:-）
+- @\*\*磊
+- @\*琢
+- @\*成
+- @Z\*o
+- @\*琨
 - [@congzhangzh](https://github.com/congzhangzh)
-- @*_
-
+- @\*\_
+- @Z\*m
 
 (If your name is masked, please contact me via my homepage email to update it with your GitHub username.)

package/README_zh.md

@@ -40,6 +40,7 @@ npm install -g @musistudio/claude-code-router
 - **`HOST`** (可选): 您可以设置服务的主机地址。如果未设置 `APIKEY`，出于安全考虑，主机地址将强制设置为 `127.0.0.1`，以防止未经授权的访问。例如：`"HOST": "0.0.0.0"`。
 - **`Providers`**: 用于配置不同的模型提供商。
 - **`Router`**: 用于设置路由规则。`default` 指定默认模型，如果未配置其他路由，则该模型将用于所有请求。
+- **`API_TIMEOUT_MS`**: API 请求超时时间，单位为毫秒。
 
 这是一个综合示例：
 
@@ -48,6 +49,7 @@ npm install -g @musistudio/claude-code-router
   "APIKEY": "your-secret-key",
   "PROXY_URL": "http://127.0.0.1:7890",
   "LOG": true,
+  "API_TIMEOUT_MS": 600000,
   "Providers": [
     {
       "name": "openrouter",
@@ -103,16 +105,20 @@ npm install -g @musistudio/claude-code-router
       "name": "modelscope",
       "api_base_url": "https://api-inference.modelscope.cn/v1/chat/completions",
       "api_key": "",
-      "models": ["Qwen/Qwen3-Coder-480B-A35B-Instruct"],
+      "models": ["Qwen/Qwen3-Coder-480B-A35B-Instruct", "Qwen/Qwen3-235B-A22B-Thinking-2507"],
       "transformer": {
         "use": [
           [
             "maxtoken",
             {
-              "max_tokens": 8192
+              "max_tokens": 65536
             }
-          ]
-        ]
+          ],
+          "enhancetool"
+        ],
+        "Qwen/Qwen3-235B-A22B-Thinking-2507": {
+          "use": ["reasoning"]
+        }
       }
     },
     {
@@ -125,9 +131,10 @@ npm install -g @musistudio/claude-code-router
           [
             "maxtoken",
             {
-              "max_tokens": 8192
+              "max_tokens": 65536
             }
-          ]
+          ],
+          "enhancetool"
         ]
       }
     }
@@ -137,6 +144,7 @@ npm install -g @musistudio/claude-code-router
     "background": "ollama,qwen2.5-coder:latest",
     "think": "deepseek,deepseek-reasoner",
     "longContext": "openrouter,google/gemini-2.5-pro-preview",
+    "longContextThreshold": 60000,
     "webSearch": "gemini,gemini-2.5-flash"
   }
 }
@@ -156,6 +164,16 @@ ccr code
 > ccr restart
 > ```
 
+### 4. UI 模式
+
+为了获得更直观的体验，您可以使用 UI 模式来管理您的配置：
+
+```shell
+ccr ui
+```
+
+这将打开一个基于 Web 的界面，您可以在其中轻松查看和编辑您的 `config.json` 文件。
+
 #### Providers
 
 `Providers` 数组是您定义要使用的不同模型提供商的地方。每个提供商对象都需要：
@@ -253,6 +271,7 @@ Transformers 允许您修改请求和响应负载，以确保与不同提供商
 -   `background`: 用于后台任务的模型。这可以是一个较小的本地模型以节省成本。
 -   `think`: 用于推理密集型任务（如计划模式）的模型。
 -   `longContext`: 用于处理长上下文（例如，> 60K 令牌）的模型。
+-   `longContextThreshold` (可选): 触发长上下文模型的令牌数阈值。如果未指定，默认为 60000。
 -   `webSearch`: 用于处理网络搜索任务，需要模型本身支持。如果使用`openrouter`需要在模型后面加上`:online`后缀。
 
 您还可以使用 `/model` 命令在 Claude Code 中动态切换模型：
@@ -415,9 +434,10 @@ jobs:
 - @Z*o
 - [@congzhangzh](https://github.com/congzhangzh)
 - @*_
+- @Z\*m
 
 （如果您的名字被屏蔽，请通过我的主页电子邮件与我联系，以便使用您的 GitHub 用户名进行更新。）
 
 
 ## 交流群
-<img src="/blog/images/wechat_group.jpg" width="200" alt="wechat_group" />
+<img src="/blog/images/wechat_group.jpg" width="200" alt="wechat_group" />

package/config.example.json

@@ -70,16 +70,20 @@
       "name": "modelscope",
       "api_base_url": "https://api-inference.modelscope.cn/v1/chat/completions",
       "api_key": "",
-      "models": ["Qwen/Qwen3-Coder-480B-A35B-Instruct"],
+      "models": ["Qwen/Qwen3-Coder-480B-A35B-Instruct", "Qwen/Qwen3-235B-A22B-Thinking-2507"],
       "transformer": {
         "use": [
           [
             "maxtoken",
             {
-              "max_tokens": 8192
+              "max_tokens": 65536
             }
-          ]
-        ]
+          ],
+          "enhancetool"
+        ],
+        "Qwen/Qwen3-235B-A22B-Thinking-2507": {
+          "use": ["reasoning"]
+        }
       }
     },
     {
@@ -92,9 +96,10 @@
           [
             "maxtoken",
             {
-              "max_tokens": 8192
+              "max_tokens": 65536
             }
-          ]
+          ],
+          "enhancetool"
         ]
       }
     }
@@ -103,8 +108,11 @@
     "default": "deepseek,deepseek-chat",
     "background": "ollama,qwen2.5-coder:latest",
     "think": "deepseek,deepseek-reasoner",
-    "longContext": "openrouter,google/gemini-2.5-pro-preview"
+    "longContext": "openrouter,google/gemini-2.5-pro-preview",
+    "longContextThreshold": 60000,
+    "webSearch": "gemini,gemini-2.5-flash"
   },
   "APIKEY": "your-secret-key",
-  "HOST": "0.0.0.0"
+  "HOST": "0.0.0.0",
+  "API_TIMEOUT_MS": 600000
 }