Merge pull request #680 from zengqinglei/docs/gemini-cli-configuration

docs: 优化Gemini CLI配置说明

README.md

@@ -410,10 +410,27 @@ export ANTHROPIC_AUTH_TOKEN="后台创建的API密钥"
 
 **Gemini CLI 设置环境变量：**
 
+**方式一（推荐）：通过 Gemini Assist API 方式访问**
+
+每账号每日享受 1000 次请求，每分钟 60 次免费限额。
+
 ```bash
+CODE_ASSIST_ENDPOINT="http://127.0.0.1:3000/gemini"  # 根据实际填写你服务器的ip地址或者域名
+GOOGLE_CLOUD_ACCESS_TOKEN="后台创建的API密钥"
+GOOGLE_GENAI_USE_GCA="true"
 GEMINI_MODEL="gemini-2.5-pro"
+```
+
+> **注意**：gemini-cli 控制台会提示 `Failed to fetch user info: 401 Unauthorized`，但使用不受任何影响。
+
+**方式二：通过 Gemini API 方式访问**
+
+免费额度极少，极易触发 429 错误。
+
+```bash
 GOOGLE_GEMINI_BASE_URL="http://127.0.0.1:3000/gemini"  # 根据实际填写你服务器的ip地址或者域名
-GEMINI_API_KEY="后台创建的API密钥"  # 使用相同的API密钥即可
+GEMINI_API_KEY="后台创建的API密钥"
+GEMINI_MODEL="gemini-2.5-pro"
 ```
 **使用 Claude Code：**
 

README_EN.md

@@ -232,21 +232,68 @@ Assign a key to each user:
 4. Set usage limits (optional)
 5. Save, note down the generated key
 
-### 4. Start Using Claude Code
+### 4. Start Using Claude Code and Gemini CLI
 
 Now you can replace the official API with your own service:
 
-**Set environment variables:**
+**Claude Code Set Environment Variables:**
+
+Default uses standard Claude account pool:
+
 ```bash
-export ANTHROPIC_BASE_URL="http://127.0.0.1:3000/api/" # Fill in your server's IP address or domain according to actual situation
+export ANTHROPIC_BASE_URL="http://127.0.0.1:3000/api/" # Fill in your server's IP address or domain
 export ANTHROPIC_AUTH_TOKEN="API key created in the backend"
 ```
 
-**Use claude:**
+**VSCode Claude Plugin Configuration:**
+
+If using VSCode Claude plugin, configure in `~/.claude/config.json`:
+
+```json
+{
+    "primaryApiKey": "crs"
+}
+```
+
+If the file doesn't exist, create it manually. Windows users path is `C:\Users\YourUsername\.claude\config.json`.
+
+**Gemini CLI Set Environment Variables:**
+
+**Method 1 (Recommended): Via Gemini Assist API**
+
+Each account enjoys 1000 requests per day, 60 requests per minute free quota.
+
+```bash
+CODE_ASSIST_ENDPOINT="http://127.0.0.1:3000/gemini"  # Fill in your server's IP address or domain
+GOOGLE_CLOUD_ACCESS_TOKEN="API key created in the backend"
+GOOGLE_GENAI_USE_GCA="true"
+GEMINI_MODEL="gemini-2.5-pro"
+```
+
+> **Note**: gemini-cli console will show `Failed to fetch user info: 401 Unauthorized`, but this doesn't affect usage.
+
+**Method 2: Via Gemini API**
+
+Very limited free quota, easily triggers 429 errors.
+
+```bash
+GOOGLE_GEMINI_BASE_URL="http://127.0.0.1:3000/gemini"  # Fill in your server's IP address or domain
+GEMINI_API_KEY="API key created in the backend"
+GEMINI_MODEL="gemini-2.5-pro"
+```
+
+**Use Claude Code:**
+
 ```bash
 claude
 ```
 
+**Use Gemini CLI:**
+
+```bash
+gemini
+```
+
 ---
 
 ## 🔧 Daily Maintenance

VERSION

@@ -1 +1 @@
-1.1.195
+1.1.197

src/routes/openaiRoutes.js

@@ -260,7 +260,8 @@ const handleResponses = async (req, res) => {
     // 判断是否为 Codex CLI 的请求
     const isCodexCLI =
       req.body?.instructions?.startsWith('You are a coding agent running in the Codex CLI') ||
-      req.body?.instructions?.startsWith('You are Codex')
+      req.body?.instructions?.startsWith('You are Codex') ||
+      req.body?.instructions?.startsWith('You are GPT-5.1 running in the Codex CLI')
 
     // 如果不是 Codex CLI 请求，则进行适配
     if (!isCodexCLI) {