@musistudio/claude-code-router 1.0.31 → 1.0.32

package/README.md

@@ -261,7 +261,24 @@ Transformers allow you to modify the request and response payloads to ensure com
 - `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.
+- `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`.
@@ -343,6 +360,17 @@ module.exports = async function router(req, config) {
 };
 ```
 
+##### 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...
+```
+
 ## 🤖 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:

package/README_zh.md

@@ -255,7 +255,24 @@ Transformers 允许您修改请求和响应负载，以确保与不同提供商
 -   `Anthropic`: 如果你只使用这一个转换器，则会直接透传请求和响应(你可以用它来接入其他支持Anthropic端点的服务商)。
 -   `deepseek`: 适配 DeepSeek API 的请求/响应。
 -   `gemini`: 适配 Gemini API 的请求/响应。
--   `openrouter`: 适配 OpenRouter API 的请求/响应。
+-   `openrouter`: 适配 OpenRouter API 的请求/响应。它还可以接受一个 `provider` 路由参数，以指定 OpenRouter 应使用哪些底层提供商。有关更多详细信息，请参阅 [OpenRouter 文档](https://openrouter.ai/docs/features/provider-routing)。请参阅下面的示例：
+    ```json
+      "transformer": {
+        "use": ["openrouter"],
+        "moonshotai/kimi-k2": {
+          "use": [
+            [
+              "openrouter",
+              {
+                "provider": {
+                  "only": ["moonshotai/fp8"]
+                }
+              }
+            ]
+          ]
+        }
+      }
+    ```
 -   `groq`: 适配 groq API 的请求/响应
 -   `maxtoken`: 设置特定的 `max_tokens` 值。
 -   `tooluse`: 优化某些模型的工具使用(通过`tool_choice`参数)。
@@ -337,6 +354,17 @@ module.exports = async function router(req, config) {
 };
 ```
 
+##### 子代理路由
+
+对于子代理内的路由，您必须在子代理提示词的**开头**包含 `<CCR-SUBAGENT-MODEL>provider,model</CCR-SUBAGENT-MODEL>` 来指定特定的提供商和模型。这样可以将特定的子代理任务定向到指定的模型。
+
+**示例：**
+
+```
+<CCR-SUBAGENT-MODEL>openrouter,anthropic/claude-3.5-sonnet</CCR-SUBAGENT-MODEL>
+请帮我分析这段代码是否存在潜在的优化空间...
+```
+
 
 ## 🤖 GitHub Actions