Update RL tools and enhance configuration management

- Modified `model_tools.py` to update default model IDs and add new RL function `rl_test_inference`.
- Enhanced `README.md` with installation instructions for submodules and updated API key usage.
- Improved `rl_cli.py` to load configuration from `~/.hermes/config.yaml` and set terminal working directory for RL tools.
- Updated `run_agent.py` to handle empty string arguments as empty objects for better JSON validation.
- Refined installation scripts to ensure submodules are cloned and installed correctly, enhancing setup experience.

run_agent.py

@@ -1764,10 +1764,16 @@ class AIAgent:
                         self._invalid_tool_retries = 0
                     
                     # Validate tool call arguments are valid JSON
+                    # Handle empty strings as empty objects (common model quirk)
                     invalid_json_args = []
                     for tc in assistant_message.tool_calls:
+                        args = tc.function.arguments
+                        # Treat empty/whitespace strings as empty object
+                        if not args or not args.strip():
+                            tc.function.arguments = "{}"
+                            continue
                         try:
-                            json.loads(tc.function.arguments)
+                            json.loads(args)
                         except json.JSONDecodeError as e:
                             invalid_json_args.append((tc.function.name, str(e)))