=== Venice.ai API 診斷 ===

1. 檢查配置
-----------------------------------
API Key: xai-MuUMjM...
Base URL: https://api.x.ai/v1
Model: grok-4-1-fast-reasoning

2. 檢查 Venice 參數
-----------------------------------
✗ Venice 參數未設定

3. 模擬 chat.php 的參數處理
-----------------------------------
Options 陣列:
Array
(
    [model] => grok-4-1-fast-reasoning
    [temperature] => 0.7
    [max_tokens] => 2000
)

4. 模擬 OpenAIClient 的請求資料
-----------------------------------
API 請求資料:
{
    "model": "grok-4-1-fast-reasoning",
    "messages": [
        {
            "role": "user",
            "content": "測試訊息"
        }
    ],
    "temperature": 0.7,
    "max_tokens": 2000
}

5. 測試實際 API 請求
-----------------------------------
請求 URL: https://api.x.ai/v1/chat/completions

HTTP 狀態碼: 200
✓ cURL 請求成功

API 回應:
{
    "id": "1dd5bdf2-cbea-8a55-864f-b5d77518a4c8",
    "object": "chat.completion",
    "created": 1767166513,
    "model": "grok-4-1-fast-reasoning",
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "收到！測試成功 😊 有什麼可以幫忙的嗎？",
                "refusal": null
            },
            "finish_reason": "stop"
        }
    ],
    "usage": {
        "prompt_tokens": 160,
        "completion_tokens": 14,
        "total_tokens": 393,
        "prompt_tokens_details": {
            "text_tokens": 160,
            "audio_tokens": 0,
            "image_tokens": 0,
            "cached_tokens": 151
        },
        "completion_tokens_details": {
            "reasoning_tokens": 219,
            "audio_tokens": 0,
            "accepted_prediction_tokens": 0,
            "rejected_prediction_tokens": 0
        },
        "num_sources_used": 0
    },
    "system_fingerprint": "fp_e5e99fa5b3"
}

=== 診斷建議 ===

✓ API 請求成功！

如果前端還是出現 404 錯誤，請檢查：
1. 是否已上傳最新的 chat.php 和 config.php
2. 是否已重啟 IIS (iisreset)
3. 瀏覽器是否有快取（Ctrl+F5 強制重新整理）

=== 診斷完成 ===