Fix inference.py env var pattern to match submission checklist

Use os.getenv("KEY", default) for API_BASE_URL and MODEL_NAME,
and os.getenv("HF_TOKEN") with no default, as required.

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

inference.py

@@ -25,9 +25,10 @@ load_dotenv()
 # Configuration
 # ---------------------------------------------------------------------------
 
-API_KEY = os.getenv("HF_TOKEN") or os.getenv("API_KEY")
-API_BASE_URL = os.getenv("API_BASE_URL") or "https://router.huggingface.co/v1"
-MODEL_NAME = os.getenv("MODEL_NAME") or "Qwen/Qwen2.5-72B-Instruct"
+API_BASE_URL = os.getenv("API_BASE_URL", "https://router.huggingface.co/v1")
+MODEL_NAME = os.getenv("MODEL_NAME", "Qwen/Qwen2.5-72B-Instruct")
+HF_TOKEN = os.getenv("HF_TOKEN")
+API_KEY = HF_TOKEN or os.getenv("API_KEY")
 
 ENV_URL = os.getenv("ENV_URL", "http://localhost:7860")
 BENCHMARK = "invoice_processing_pipeline"