Add Codex load balancing documentation and refine JSON handling logic

- Updated README and README_CN to include a guide for configuring multiple account load balancing with CLI Proxy API.
- Enhanced JSON handling in gemini translators by differentiating object and string outputs.
- Added commented debug logging for Gemini CLI response conversion.

README.md

@@ -430,6 +430,29 @@ export ANTHROPIC_MODEL=qwen3-coder-plus
 export ANTHROPIC_SMALL_FAST_MODEL=qwen3-coder-flash
 ```
 
+## Codex with multiple account load balancing
+
+Start CLI Proxy API server, and then edit the `~/.codex/config.toml` and `~/.codex/auth.json` files.
+
+config.toml:
+```toml
+model_provider = "cliproxyapi"
+model = "gpt-5" # You can use any of the models that we support.
+model_reasoning_effort = "high"
+
+[model_providers.cliproxyapi]
+name = "cliproxyapi"
+base_url = "http://127.0.0.1:8317/v1"
+wire_api = "responses"
+```
+
+auth.json:
+```json
+{
+  "OPENAI_API_KEY": "sk-dummy"
+}
+```
+
 ## Run with Docker
 
 Run the following command to login (Gemini OAuth on port 8085): 

README_CN.md

@@ -424,6 +424,28 @@ export ANTHROPIC_MODEL=qwen3-coder-plus
 export ANTHROPIC_SMALL_FAST_MODEL=qwen3-coder-flash
 ```
 
+## Codex 多账户负载均衡
+
+启动 CLI Proxy API 服务器, 修改 `~/.codex/config.toml` 和 `~/.codex/auth.json` 文件。
+
+config.toml:
+```toml
+model_provider = "cliproxyapi"
+model = "gpt-5" # 你可以使用任何我们支持的模型
+model_reasoning_effort = "high"
+
+[model_providers.cliproxyapi]
+name = "cliproxyapi"
+base_url = "http://127.0.0.1:8317/v1"
+wire_api = "responses"
+```
+
+auth.json:
+```json
+{
+  "OPENAI_API_KEY": "sk-dummy"
+}
+```
 
 ## 使用 Docker 运行
 

internal/translator/gemini-cli/openai/responses/cli_openai-responses_request.go

@@ -10,5 +10,6 @@ import (
 func ConvertOpenAIResponsesRequestToGeminiCLI(modelName string, inputRawJSON []byte, stream bool) []byte {
 	rawJSON := bytes.Clone(inputRawJSON)
 	rawJSON = ConvertOpenAIResponsesRequestToGemini(modelName, rawJSON, stream)
+	// log.Debug(string(rawJSON))
 	return ConvertGeminiRequestToGeminiCLI(modelName, rawJSON, stream)
 }

internal/translator/gemini/openai/responses/gemini_openai-responses_request.go

@@ -109,7 +109,11 @@ func ConvertOpenAIResponsesRequestToGemini(modelName string, inputRawJSON []byte
 				// Parse output JSON string and set as response content
 				if output != "" {
 					outputResult := gjson.Parse(output)
-					functionResponse, _ = sjson.SetRaw(functionResponse, "functionResponse.response.content", outputResult.Raw)
+					if outputResult.IsObject() {
+						functionResponse, _ = sjson.SetRaw(functionResponse, "functionResponse.response.content", outputResult.String())
+					} else {
+						functionResponse, _ = sjson.Set(functionResponse, "functionResponse.response.content", outputResult.String())
+					}
 				}
 
 				functionContent, _ = sjson.SetRaw(functionContent, "parts.-1", functionResponse)