切换 Tiantoken 并删除旧 Vidu 音效

新增 TIANTOKEN_BASE_URL / TIANTOKEN_API_KEY 配置并切换文本与图片链路

保留 Suno VectorEngine 路径，删除旧 Vidu submit/poll/builder 实现

同步脚本、文档、测试与运行时 provider 路由

.env.example

@@ -1,8 +1,8 @@
 # Server-side OpenAI-compatible LLM endpoint base URL.
-LLM_BASE_URL="https://api.vectorengine.cn/v1"
+LLM_BASE_URL="https://api.tiantoken.com/v1"
 
 # Server-side API key used by the local Vite proxy.
-# Recommended: set `LLM_API_KEY` locally, or use `VECTOR_ENGINE_API_KEY`
+# Recommended: set `LLM_API_KEY` locally, or use `TIANTOKEN_API_KEY`
 # through the Rust api-server proxy.
 # Legacy compatibility: `VITE_LLM_API_KEY` is still supported by the proxy,
 # but it should not be relied on by browser code.
@@ -122,7 +122,7 @@ WECHAT_MINIPROGRAM_MESSAGE_ENCODING_AES_KEY=""
 # Model name for chat completions.
 VITE_LLM_MODEL="gpt-5.4-mini"
 GENARRATIVE_LLM_PROVIDER="openai-compatible"
-GENARRATIVE_LLM_BASE_URL="https://api.vectorengine.cn/v1"
+GENARRATIVE_LLM_BASE_URL="https://api.tiantoken.com/v1"
 GENARRATIVE_LLM_API_KEY=""
 GENARRATIVE_LLM_MODEL="gpt-5.4-mini"
 
@@ -130,10 +130,15 @@ GENARRATIVE_LLM_MODEL="gpt-5.4-mini"
 DASHSCOPE_BASE_URL="https://dashscope.aliyuncs.com/api/v1"
 DASHSCOPE_API_KEY="YOUR_DASHSCOPE_API_KEY"
 
-# VectorEngine LLM and GPT-image-2 / Gemini image generation config.
+# Tiantoken LLM and GPT-image-2 / Gemini image generation config.
+TIANTOKEN_BASE_URL="https://api.tiantoken.com"
+TIANTOKEN_API_KEY=""
+TIANTOKEN_IMAGE_REQUEST_TIMEOUT_MS="1000000"
+
+# VectorEngine is retained for Suno audio generation only.
 VECTOR_ENGINE_BASE_URL="https://api.vectorengine.cn"
 VECTOR_ENGINE_API_KEY=""
-VECTOR_ENGINE_IMAGE_REQUEST_TIMEOUT_MS="1000000"
+VECTOR_ENGINE_AUDIO_REQUEST_TIMEOUT_MS="180000"
 
 # ElevenLabs editor sound-effect generation is server-side only.
 ELEVENLABS_BASE_URL="https://api.elevenlabs.io"