docs: update .env.example to reflect all required env vars

All parameters are now required (no defaults in code), so .env.example
lists them all uncommented. Added NVIDIA_ENABLE_THINKING.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

server/.env.example

@@ -2,11 +2,12 @@
 NVIDIA_API_KEY=your_nvidia_api_key_here
 APP_PASSWORD=your_shared_password_here
 
-# Opzionali — i default sono in app/config.py
+# Parametri server
-# NVIDIA_BASE_URL=https://integrate.api.nvidia.com/v1
+NVIDIA_BASE_URL=https://integrate.api.nvidia.com/v1
-# NVIDIA_MODEL=nvidia/nemotron-3-ultra-550b-a55b
+NVIDIA_MODEL=nvidia/nemotron-3-ultra-550b-a55b
-# NVIDIA_TIMEOUT_SECONDS=120
+NVIDIA_TIMEOUT_SECONDS=120
-# NVIDIA_MAX_TOKENS=16384
+NVIDIA_MAX_TOKENS=16384
-# NVIDIA_TEMPERATURE=1.0
+NVIDIA_TEMPERATURE=1.0
-# NVIDIA_TOP_P=0.95
+NVIDIA_TOP_P=0.95
-# NVIDIA_REASONING_BUDGET=2048
+NVIDIA_REASONING_BUDGET=2048
+NVIDIA_ENABLE_THINKING=false

server/app/config.py

@@ -4,13 +4,14 @@ from pydantic_settings import BaseSettings
 class Settings(BaseSettings):
     nvidia_api_key: str
     app_password: str
-    nvidia_base_url: str = "https://integrate.api.nvidia.com/v1"
+    nvidia_base_url: str
-    nvidia_model: str = "nvidia/nemotron-3-ultra-550b-a55b"
+    nvidia_model: str
-    nvidia_timeout_seconds: int = 120
+    nvidia_timeout_seconds: int
-    nvidia_max_tokens: int = 16384
+    nvidia_max_tokens: int
-    nvidia_temperature: float = 1.0
+    nvidia_temperature: float
-    nvidia_top_p: float = 0.95
+    nvidia_top_p: float
-    nvidia_reasoning_budget: int = 2048
+    nvidia_reasoning_budget: int
+    nvidia_enable_thinking: bool
 
     model_config = {"env_file": ".env"}
 

server/app/main.py

@@ -68,7 +68,7 @@ async def generate_recipes(request: RecipeRequest):
                 top_p=settings.nvidia_top_p,
                 max_tokens=settings.nvidia_max_tokens,
                 extra_body={
-                    "chat_template_kwargs": {"enable_thinking": True},
+                    "chat_template_kwargs": {"enable_thinking": settings.nvidia_enable_thinking},
                     "reasoning_budget": settings.nvidia_reasoning_budget,
                 },
                 stream=True,