refactor: externalize hardcoded model config and clean up robustness plan

- Add openai_model, tts_minimax_model, tts_elevenlabs_model, tts_edge_voice,
  antigravity_model to Settings; set image_model default to nano-banana-pro
- Update provider_router._get_default_config to read from settings
- Add nul to .gitignore (Windows artifact)
- Mark all robustness tasks as completed in dev-plan.md

backend/app/core/config.py

@@ -41,8 +41,13 @@ class Settings(BaseSettings):
 
     # AI Model Configuration
     text_model: str = "gemini-2.0-flash"
+    openai_model: str = "gpt-4o-mini"
     tts_model: str = ""
-    image_model: str = ""
+    image_model: str = "nano-banana-pro"
+    tts_minimax_model: str = "speech-2.6-turbo"
+    tts_elevenlabs_model: str = "eleven_multilingual_v2"
+    tts_edge_voice: str = "zh-CN-XiaoxiaoNeural"
+    antigravity_model: str = "gemini-3-pro-image"
 
     # Provider routing (ordered lists)
     text_providers: list[str] = Field(default_factory=lambda: ["gemini"])

backend/app/services/provider_router.py

@@ -98,7 +98,7 @@ def _get_default_config(adapter_name: str) -> AdapterConfig | None:
     if adapter_name == "openai":
         return AdapterConfig(
             api_key=getattr(settings, "openai_api_key", ""),
-            model="gpt-4o-mini", # 这里可以从 settings 读取，看需求
+            model=settings.openai_model,
             timeout_ms=60000,
         )
 
@@ -106,7 +106,7 @@ def _get_default_config(adapter_name: str) -> AdapterConfig | None:
     if adapter_name in ("cqtai"):
         return AdapterConfig(
             api_key=getattr(settings, "cqtai_api_key", ""),
-            model="nano-banana-pro", # 默认使用 Pro
+            model=settings.image_model or "nano-banana-pro",
             timeout_ms=120000,
         )
     if adapter_name == "image_primary":
@@ -128,7 +128,7 @@ def _get_default_config(adapter_name: str) -> AdapterConfig | None:
         # 我们这里暂时返回基础配置。
         return AdapterConfig(
             api_key=getattr(settings, "minimax_api_key", ""),
-            model="speech-2.6-turbo",
+            model=settings.tts_minimax_model,
             timeout_ms=60000,
         )