fix(inference): handle empty env vars gracefully to prevent httpx crashes

inference.py

@@ -22,10 +22,10 @@ from openai import OpenAI
 load_dotenv()
 
 # ── Config ────────────────────────────────────────────────────────────────────
-API_BASE_URL = os.getenv("API_BASE_URL", "https://api.openai.com/v1")
-MODEL_NAME   = os.getenv("MODEL_NAME", "gpt-4o-mini")
-HF_TOKEN     = os.getenv("HF_TOKEN")
-ENV_URL      = os.getenv("ENV_URL", "http://localhost:7860")
+API_BASE_URL = os.getenv("API_BASE_URL") or "https://api.openai.com/v1"
+MODEL_NAME   = os.getenv("MODEL_NAME") or "gpt-4o-mini"
+HF_TOKEN     = os.getenv("HF_TOKEN") or os.getenv("API_KEY")
+ENV_URL      = os.getenv("ENV_URL") or "http://localhost:7860"
 BENCHMARK    = "code-security-review"
 
 if not HF_TOKEN: