@wengine-ai/claude-code-router-next 2.1.1

package/README.md

@@ -0,0 +1,720 @@
+![](blog/images/claude-code-router-img.png)
+
+[![](https://img.shields.io/badge/%F0%9F%87%A8%F0%9F%87%B3-%E4%B8%AD%E6%96%87%E7%89%88-ff0000?style=flat)](README_zh.md)
+[![Discord](https://img.shields.io/badge/Discord-%235865F2.svg?&logo=discord&logoColor=white)](https://discord.gg/rdftVMaUcS)
+[![](https://img.shields.io/github/license/musistudio/claude-code-router)](https://github.com/musistudio/claude-code-router/blob/main/LICENSE)
+
+<hr>
+
+> [Progressive Disclosure of Agent Tools from the Perspective of CLI Tool Style](/blog/en/progressive-disclosure-of-agent-tools-from-the-perspective-of-cli-tool-style.md)
+
+> A powerful tool to route Claude Code requests to different models and customize any request.
+
+![](blog/images/claude-code.png)
+
+## ✨ 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.
+- **CLI Model Management**: Manage models and providers directly from the terminal with `ccr model`.
+- **GitHub Actions Integration**: Trigger Claude Code tasks in your GitHub workflows.
+- **Plugin System**: Extend functionality with custom transformers.
+
+## 🚀 Getting Started
+
+### 1. Installation
+
+You can install Claude Code Router either from the npm registry or directly from this GitHub repository for the latest development version.
+
+#### Option A: Install from npm registry (Stable)
+
+First, ensure you have [Claude Code](https://docs.anthropic.com/en/docs/claude-code/quickstart) installed:
+
+```shell
+npm install -g @anthropic-ai/claude-code
+```
+
+Then, install Claude Code Router:
+
+```shell
+npm install -g claude-code-router-next
+```
+
+#### Option B: Install from GitHub (Latest Development Version)
+
+If you want to use the latest features and bug fixes directly from the source code:
+
+1. **Uninstall the current version first** (to prevent command conflicts):
+   ```shell
+   npm uninstall -g claude-code-router-next @musistudio/claude-code-router @wengine-ai/claude-code-router
+   ```
+
+2. **Clone and link locally** (recommended for developers):
+   ```shell
+   git clone https://github.com/xiaoliu10/claude-code-router-next.git
+   cd claude-code-router-next
+   pnpm install
+   pnpm build
+   npm link
+   ```
+
+   *Alternatively, install directly from GitHub globally:*
+   ```shell
+   npm install -g github:xiaoliu10/claude-code-router-next
+   ```
+
+#### 🔄 Migrating from the Official Upstream (@musistudio/claude-code-router)
+
+If you are currently using the upstream community version `@musistudio/claude-code-router` and want to switch to this repository's version (`claude-code-router-next`) for advanced features (e.g. enhanced token-limit UI bars, DeepSeek thinking compatibilities, active health probes):
+
+1. **Uninstall the upstream community version**:
+   ```shell
+   npm uninstall -g @musistudio/claude-code-router
+   ```
+
+2. **Install this version**:
+   ```shell
+   npm install -g claude-code-router-next
+   ```
+
+### 2. Configuration
+
+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`. When set to `false`, no log files will be created. Default is `true`.
+- **`LOG_LEVEL`** (optional): Set the logging level. Available options are: `"fatal"`, `"error"`, `"warn"`, `"info"`, `"debug"`, `"trace"`. Default is `"debug"`.
+- **Logging Systems**: The Claude Code Router uses two separate logging systems:
+  - **Server-level logs**: HTTP requests, API calls, and server events are logged using pino in the `~/.claude-code-router/logs/` directory with filenames like `ccr-*.log`
+  - **Application-level logs**: Routing decisions and business logic events are logged in `~/.claude-code-router/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"`.
+- **`HOST`** (optional): You can set the host address for the server. If `APIKEY` is not set, the host will be forced to `127.0.0.1` for security reasons to prevent unauthorized access. Example: `"HOST": "0.0.0.0"`.
+- **`NON_INTERACTIVE_MODE`** (optional): When set to `true`, enables compatibility with non-interactive environments like GitHub Actions, Docker containers, or other CI/CD systems. This sets appropriate environment variables (`CI=true`, `FORCE_COLOR=0`, etc.) and configures stdin handling to prevent the process from hanging in automated environments. Example: `"NON_INTERACTIVE_MODE": true`.
+
+- **`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.
+
+#### Environment Variable Interpolation
+
+Claude Code Router supports environment variable interpolation for secure API key management. You can reference environment variables in your `config.json` using either `$VAR_NAME` or `${VAR_NAME}` syntax:
+
+```json
+{
+  "OPENAI_API_KEY": "$OPENAI_API_KEY",
+  "GEMINI_API_KEY": "${GEMINI_API_KEY}",
+  "Providers": [
+    {
+      "name": "openai",
+      "api_base_url": "https://api.openai.com/v1/chat/completions",
+      "api_key": "$OPENAI_API_KEY",
+      "models": ["gpt-5", "gpt-5-mini"]
+    }
+  ]
+}
+```
+
+This allows you to keep sensitive API keys in environment variables instead of hardcoding them in configuration files. The interpolation works recursively through nested objects and arrays.
+
+Here is a comprehensive example:
+
+```json
+{
+  "APIKEY": "your-secret-key",
+  "PROXY_URL": "http://127.0.0.1:7890",
+  "LOG": true,
+  "API_TIMEOUT_MS": 600000,
+  "NON_INTERACTIVE_MODE": false,
+  "Providers": [
+    {
+      "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",
+        "anthropic/claude-3.7-sonnet:thinking"
+      ],
+      "transformer": {
+        "use": ["openrouter"]
+      }
+    },
+    {
+      "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"]
+        }
+      }
+    },
+    {
+      "name": "ollama",
+      "api_base_url": "http://localhost:11434/v1/chat/completions",
+      "api_key": "ollama",
+      "models": ["qwen2.5-coder:latest"]
+    },
+    {
+      "name": "gemini",
+      "api_base_url": "https://generativelanguage.googleapis.com/v1beta/models/",
+      "api_key": "sk-xxx",
+      "models": ["gemini-2.5-flash", "gemini-2.5-pro"],
+      "transformer": {
+        "use": ["gemini"]
+      }
+    },
+    {
+      "name": "volcengine",
+      "api_base_url": "https://ark.cn-beijing.volces.com/api/v3/chat/completions",
+      "api_key": "sk-xxx",
+      "models": ["deepseek-v3-250324", "deepseek-r1-250528"],
+      "transformer": {
+        "use": ["deepseek"]
+      }
+    },
+    {
+      "name": "modelscope",
+      "api_base_url": "https://api-inference.modelscope.cn/v1/chat/completions",
+      "api_key": "",
+      "models": ["Qwen/Qwen3-Coder-480B-A35B-Instruct", "Qwen/Qwen3-235B-A22B-Thinking-2507"],
+      "transformer": {
+        "use": [
+          [
+            "maxtoken",
+            {
+              "max_tokens": 65536
+            }
+          ],
+          "enhancetool"
+        ],
+        "Qwen/Qwen3-235B-A22B-Thinking-2507": {
+          "use": ["reasoning"]
+        }
+      }
+    },
+    {
+      "name": "dashscope",
+      "api_base_url": "https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions",
+      "api_key": "",
+      "models": ["qwen3-coder-plus"],
+      "transformer": {
+        "use": [
+          [
+            "maxtoken",
+            {
+              "max_tokens": 65536
+            }
+          ],
+          "enhancetool"
+        ]
+      }
+    },
+    {
+      "name": "aihubmix",
+      "api_base_url": "https://aihubmix.com/v1/chat/completions",
+      "api_key": "sk-",
+      "models": [
+        "Z/glm-4.5",
+        "claude-opus-4-20250514",
+        "gemini-2.5-pro"
+      ]
+    }
+  ],
+  "Router": {
+    "default": "deepseek,deepseek-chat",
+    "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"
+  }
+}
+```
+
+### 🔑 API Key / Token Guide
+
+To use the router, you need to acquire API Keys from your preferred LLM providers. Below are guides for some popular providers:
+
+#### 1. Zhipu AI (BigModel / GLM CODING PLAN)
+*   **Platform**: Zhipu BigModel Platform (sponsored partner)
+*   **Link**: [Zhipu AI BigModel Platform](https://www.bigmodel.cn/claude-code?ic=RRVJPB5SII) (Use this referral link for a 10% discount on GLM CODING PLAN)
+*   **Acquisition Method**:
+    1. Register and log in using the link above.
+    2. Go to the top-right **Console** -> **API Keys**.
+    3. Copy your API Key.
+
+    GLM CODING PLAN quota information is fetched with this API Key, so you no longer need to configure a web token or `quotaToken`.
+
+#### 2. Alibaba Cloud (DashScope / Bailian / Qwen-Coder)
+*   **Platform**: Alibaba Cloud Bailian (highly capable Qwen-Coder models)
+*   **Link**: [Alibaba Cloud Bailian Console](https://bailian.console.aliyun.com/)
+*   **Acquisition Methods**:
+    *   **Method A: Standard Developer API Key (For Request Routing)**
+        1. Log in to Alibaba Cloud and enable the "Bailian" model service.
+        2. Go to the Bailian Console, click on your **profile icon** in the top-right corner.
+        3. Click on **API-KEY** in the dropdown.
+        4. Click **Create New API-KEY** and copy the generated key.
+    *   **Method B: Aliyun Console Cookie (For Quota Visualization in UI)**
+        If you want the Claude Code Router UI to fetch and display your monthly **Qwen Coding Plan** quota progress bars, you need to configure your console session `Cookie` as `quotaToken` in your configuration:
+        1. Log in to the [Alibaba Cloud Bailian Console](https://bailian.console.aliyun.com/).
+        2. Open your browser's Developer Tools (F12) and switch to the **Network** tab.
+        3. Click the **Refresh** (用量刷新) button on the console's usage cards.
+        4. Look for an API request starting with `api.json?action=BroadScope...` in the network log.
+        5. Select the request, find the **`Cookie`** header under **Request Headers**, and copy its entire value.
+        6. Paste this copied cookie string as the **`quotaToken`** property inside the Alibaba Cloud provider block in your `config.json`.
+
+        ![Alibaba Cloud Quota Cookie Acquisition](blog/images/aliyun-quota-auth.png)
+
+### 3. Running Claude Code with the Router
+
+Start Claude Code using the router:
+
+```shell
+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.
+
+![UI](/blog/images/ui.png)
+
+#### Usage Statistics
+
+The dashboard includes a built-in **Usage Statistics** panel at the bottom of the main page. Once your requests are routed through Claude Code Router, usage records are collected automatically and displayed in the UI.
+
+You can use it to view:
+
+- Total requests
+- Input and output tokens
+- Average TTFT
+- Average generation speed
+- Success rate
+- Daily usage chart
+- Detailed request records with filters and pagination
+
+How to use it:
+
+1. Start the router service with `ccr start`
+2. Open the UI with `ccr ui`
+3. Send requests through Claude Code Router, for example with `ccr code`
+4. Return to the main dashboard and check the **Usage Statistics** panel
+
+Usage data is stored in:
+
+```shell
+~/.claude-code-router/data/usage.jsonl
+```
+
+You can also filter records by date range, provider, model, and scenario directly in the UI.
+
+If the `token-speed` plugin is enabled, the panel will also show TTFT and tokens-per-second metrics. Without that plugin, token counts and request statistics still work, but TTFT and speed may appear as `-`.
+
+For API-based access, Claude Code Router also provides:
+
+- `GET /api/usage` — paginated records with summary
+- `GET /api/usage/summary` — summary only
+- `DELETE /api/usage` — clear usage data
+
+### 5. CLI Model Management
+
+For users who prefer terminal-based workflows, you can use the interactive CLI model selector:
+
+```shell
+ccr model
+```
+![](blog/images/models.gif)
+
+This command provides an interactive interface to:
+
+- View current configuration:
+- See all configured models (default, background, think, longContext, webSearch, image)
+- Switch models: Quickly change which model is used for each router type
+- Add new models: Add models to existing providers
+- Create new providers: Set up complete provider configurations including:
+   - Provider name and API endpoint
+   - API key
+   - Available models
+   - Transformer configuration with support for:
+     - Multiple transformers (openrouter, deepseek, gemini, etc.)
+     - Transformer options (e.g., maxtoken with custom limits)
+     - Provider-specific routing (e.g., OpenRouter provider preferences)
+
+The CLI tool validates all inputs and provides helpful prompts to guide you through the configuration process, making it easy to manage complex setups without editing JSON files manually.
+
+### 6. Presets Management
+
+Presets allow you to save, share, and reuse configurations easily. You can export your current configuration as a preset and install presets from files or URLs.
+
+```shell
+# Export current configuration as a preset
+ccr preset export my-preset
+
+# Export with metadata
+ccr preset export my-preset --description "My OpenAI config" --author "Your Name" --tags "openai,production"
+
+# Install a preset from local directory
+ccr preset install /path/to/preset
+
+# List all installed presets
+ccr preset list
+
+# Show preset information
+ccr preset info my-preset
+
+# Delete a preset
+ccr preset delete my-preset
+```
+
+**Preset Features:**
+- **Export**: Save your current configuration as a preset directory (with manifest.json)
+- **Install**: Install presets from local directories
+- **Sensitive Data Handling**: API keys and other sensitive data are automatically sanitized during export (marked as `{{field}}` placeholders)
+- **Dynamic Configuration**: Presets can include input schemas for collecting required information during installation
+- **Version Control**: Each preset includes version metadata for tracking updates
+
+**Preset File Structure:**
+```
+~/.claude-code-router/presets/
+├── my-preset/
+│   └── manifest.json    # Contains configuration and metadata
+```
+
+### 7. Activate Command (Environment Variables Setup)
+
+The `activate` command allows you to set up environment variables globally in your shell, enabling you to use the `claude` command directly or integrate Claude Code Router with applications built using the Agent SDK.
+
+To activate the environment variables, run:
+
+```shell
+eval "$(ccr activate)"
+```
+
+This command outputs the necessary environment variables in shell-friendly format, which are then set in your current shell session. After activation, you can:
+
+- **Use `claude` command directly**: Run `claude` commands without needing to use `ccr code`. The `claude` command will automatically route requests through Claude Code Router.
+- **Integrate with Agent SDK applications**: Applications built with the Anthropic Agent SDK will automatically use the configured router and models.
+
+The `activate` command sets the following environment variables:
+
+- `ANTHROPIC_AUTH_TOKEN`: API key from your configuration
+- `ANTHROPIC_BASE_URL`: The local router endpoint (default: `http://127.0.0.1:3456`)
+- `NO_PROXY`: Set to `127.0.0.1` to prevent proxy interference
+- `DISABLE_TELEMETRY`: Disables telemetry
+- `DISABLE_COST_WARNINGS`: Disables cost warnings
+- `API_TIMEOUT_MS`: API timeout from your configuration
+
+> **Note**: Make sure the Claude Code Router service is running (`ccr start`) before using the activated environment variables. The environment variables are only valid for the current shell session. To make them persistent, you can add `eval "$(ccr activate)"` to your shell configuration file (e.g., `~/.zshrc` or `~/.bashrc`).
+
+#### 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.
+
+#### 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
+          }
+        ]
+      ]
+    }
+  }
+  ```
+
+**Available Built-in Transformers:**
+
+- `Anthropic`:If you use only the `Anthropic` transformer, it will preserve the original request and response parameters(you can use it to connect directly to an Anthropic endpoint).
+- `deepseek`: Adapts requests/responses for DeepSeek API.
+- `gemini`: Adapts requests/responses for Gemini API.
+- `openrouter`: Adapts requests/responses for OpenRouter API. It can also accept a `provider` routing parameter to specify which underlying providers OpenRouter should use. For more details, refer to the [OpenRouter documentation](https://openrouter.ai/docs/features/provider-routing). See an example below:
+  ```json
+    "transformer": {
+      "use": ["openrouter"],
+      "moonshotai/kimi-k2": {
+        "use": [
+          [
+            "openrouter",
+            {
+              "provider": {
+                "only": ["moonshotai/fp8"]
+              }
+            }
+          ]
+        ]
+      }
+    }
+  ```
+- `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).
+- `reasoning`: Used to process the `reasoning_content` field.
+- `sampling`: Used to process sampling information fields such as `temperature`, `top_p`, `top_k`, and `repetition_penalty`.
+- `enhancetool`: Adds a layer of error tolerance to the tool call parameters returned by the LLM (this will cause the tool call information to no longer be streamed).
+- `cleancache`: Clears the `cache_control` field from requests.
+- `vertex-gemini`: Handles the Gemini API using Vertex authentication.
+- `chutes-glm` Unofficial support for GLM 4.5 model via Chutes [chutes-glm-transformer.js](https://gist.github.com/vitobotta/2be3f33722e05e8d4f9d2b0138b8c863).
+- `qwen-cli` (experimental): Unofficial support for qwen3-coder-plus model via Qwen CLI [qwen-cli.js](https://gist.github.com/musistudio/f5a67841ced39912fd99e42200d5ca8b).
+- `rovo-cli` (experimental): Unofficial support for gpt-5 via Atlassian Rovo Dev CLI [rovo-cli.js](https://gist.github.com/SaseQ/c2a20a38b11276537ec5332d1f7a5e53).
+
+**Custom Transformers:**
+
+You can also create your own transformers and load them via the `transformers` field in `config.json`.
+
+```json
+{
+  "transformers": [
+    {
+      "path": "/User/xxx/.claude-code-router/plugins/gemini-cli.js",
+      "options": {
+        "project": "xxx"
+      }
+    }
+  ]
+}
+```
+
+#### Router
+
+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).
+- `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.
+- `image` (beta): Used for handling image-related tasks (supported by CCR’s built-in agent). If the model does not support tool calling, you need to set the `config.forceUseImageAgent` property to `true`.
+
+- You can also switch models dynamically in Claude Code with the `/model` command:
+`/model provider_name,model_name`
+Example: `/model openrouter,anthropic/claude-3.5-sonnet`
+
+#### Custom Router
+
+For more advanced routing logic, you can specify a custom router script via the `CUSTOM_ROUTER_PATH` in your `config.json`. This allows you to implement complex routing rules beyond the default scenarios.
+
+In your `config.json`:
+
+```json
+{
+  "CUSTOM_ROUTER_PATH": "/User/xxx/.claude-code-router/custom-router.js"
+}
+```
+
+The custom router file must be a JavaScript module that exports an `async` function. This function receives the request object and the config object as arguments and should return the provider and model name as a string (e.g., `"provider_name,model_name"`), or `null` to fall back to the default router.
+
+Here is an example of a `custom-router.js` based on `custom-router.example.js`:
+
+```javascript
+// /User/xxx/.claude-code-router/custom-router.js
+
+/**
+ * A custom router function to determine which model to use based on the request.
+ *
+ * @param {object} req - The request object from Claude Code, containing the request body.
+ * @param {object} config - The application's config object.
+ * @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;
+
+  if (userMessage && userMessage.includes("explain this code")) {
+    // Use a powerful model for code explanation
+    return "openrouter,anthropic/claude-3.5-sonnet";
+  }
+
+  // Fallback to the default router configuration
+  return null;
+};
+```
+
+##### Subagent Routing
+
+For routing within subagents, you must specify a particular provider and model by including `<CCR-SUBAGENT-MODEL>provider,model</CCR-SUBAGENT-MODEL>` at the **beginning** of the subagent's prompt. This allows you to direct specific subagent tasks to designated models.
+
+**Example:**
+
+```
+<CCR-SUBAGENT-MODEL>openrouter,anthropic/claude-3.5-sonnet</CCR-SUBAGENT-MODEL>
+Please help me analyze this code snippet for potential optimizations...
+```
+
+## Status Line (Beta)
+
+To better monitor the status of Claude Code Router at runtime, the project includes a built-in status line tool that can be enabled from the UI.
+
+![statusline-config.png](/blog/images/statusline-config.png)
+
+How to use it:
+
+1. Open the UI with `ccr ui`
+2. Enable **StatusLine** in the configuration panel
+3. Save the configuration and restart the service with `ccr restart`
+4. Start Claude Code with `ccr code`
+
+> The built-in status line is injected automatically when Claude Code is launched with `ccr code`.
+
+The status line supports token-related variables such as:
+
+- `{{inputTokens}}`
+- `{{outputTokens}}`
+- `{{tokenSpeed}}`
+
+This makes it possible to display input tokens, output tokens, and streaming speed directly in the terminal while requests are running.
+
+The effect is as follows:
+
+![statusline](/blog/images/statusline.png)
+
+## 🤖 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:
+
+```yaml
+name: Claude Code
+
+on:
+  issue_comment:
+    types: [created]
+  # ... other triggers
+
+jobs:
+  claude:
+    if: |
+      (github.event_name == 'issue_comment' && contains(github.event.comment.body, '@claude')) ||
+      # ... other conditions
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: read
+      issues: read
+      id-token: write
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
+
+      - name: Prepare Environment
+        run: |
+          curl -fsSL https://bun.sh/install | bash
+          mkdir -p $HOME/.claude-code-router
+          cat << 'EOF' > $HOME/.claude-code-router/config.json
+          {
+            "log": true,
+            "NON_INTERACTIVE_MODE": true,
+            "OPENAI_API_KEY": "${{ secrets.OPENAI_API_KEY }}",
+            "OPENAI_BASE_URL": "https://api.deepseek.com",
+            "OPENAI_MODEL": "deepseek-chat"
+          }
+          EOF
+        shell: bash
+
+      - name: Start Claude Code Router
+        run: |
+          nohup ~/.bun/bin/bunx claude-code-router-next@latest start &
+        shell: bash
+
+      - name: Run Claude Code
+        id: claude
+        uses: anthropics/claude-code-action@beta
+        env:
+          ANTHROPIC_BASE_URL: http://localhost:3456
+        with:
+          anthropic_api_key: "any-string-is-ok"
+```
+
+> **Note**: When running in GitHub Actions or other automation environments, make sure to set `"NON_INTERACTIVE_MODE": true` in your configuration to prevent the process from hanging due to stdin handling issues.
+
+This setup allows for interesting automations, like running tasks during off-peak hours to reduce API costs.
+
+## 📝 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)
+- [GLM-4.6 Supports Reasoning and Interleaved Thinking](blog/en/glm-4.6-supports-reasoning.md)
+
+## ❤️ Support & Sponsoring
+
+If you find this project helpful, please consider sponsoring its development. Your support is greatly appreciated!
+
+[![ko-fi](https://ko-fi.com/img/githubbutton_sm.svg)](https://ko-fi.com/F1F31GN2GM)
+
+[Paypal](https://paypal.me/musistudio1999)
+
+<table>
+  <tr>
+    <td><img src="/blog/images/alipay.jpg" width="200" alt="Alipay" /></td>
+    <td><img src="/blog/images/wechat.jpg" width="200" alt="WeChat Pay" /></td>
+  </tr>
+</table>
+