Fix: Read LLM provider config at runtime for UI updates

src/agent/llm_client.py

@@ -45,9 +45,7 @@ GROQ_MODEL = "qwen/qwen3-32b"  # Free tier: 60 req/min, fast inference
 TEMPERATURE = 0  # Deterministic for factoid answers
 MAX_TOKENS = 4096
 
-# LLM Provider Selection
-LLM_PROVIDER = os.getenv("LLM_PROVIDER", "gemini").lower()  # "gemini", "huggingface", "groq", or "claude"
-ENABLE_LLM_FALLBACK = os.getenv("ENABLE_LLM_FALLBACK", "false").lower() == "true"
+# LLM Provider Selection (removed - now read at runtime for UI flexibility)
 
 # ============================================================================
 # Logging Setup
@@ -172,7 +170,9 @@ def _call_with_fallback(function_name: str, *args, **kwargs) -> Any:
     Raises:
         Exception: If selected provider fails and fallback disabled, or all providers fail
     """
-    primary_provider = LLM_PROVIDER
+    # Read config at runtime for UI flexibility
+    primary_provider = os.getenv("LLM_PROVIDER", "gemini").lower()
+    enable_fallback = os.getenv("ENABLE_LLM_FALLBACK", "false").lower() == "true"
 
     # Define fallback order (excluding primary provider)
     all_providers = ["gemini", "huggingface", "groq", "claude"]
@@ -187,7 +187,7 @@ def _call_with_fallback(function_name: str, *args, **kwargs) -> Any:
         logger.warning(f"[{function_name}] Primary provider {primary_provider} failed: {primary_error}")
 
         # If fallback disabled, raise immediately
-        if not ENABLE_LLM_FALLBACK:
+        if not enable_fallback:
             logger.error(f"[{function_name}] Fallback disabled. Failing fast.")
             raise Exception(
                 f"{function_name} failed with {primary_provider}: {primary_error}. "