Add RL training configuration and tools

- Updated `.env.example` to include Tinker and WandB API keys for reinforcement learning training.
- Enhanced `model_tools.py` to clarify configuration options and streamline the RL training process.
- Expanded `README.md` with detailed instructions for setting up RL training using Tinker and WandB.
- Modified `hermes_cli` files to integrate RL training tools and ensure proper configuration checks.
- Improved `rl_training_tool.py` to reflect changes in training parameters and configuration management.

hermes_cli/config.py

@@ -151,6 +151,20 @@ OPTIONAL_ENV_VARS = {
         "tools": ["image_generate"],
         "password": True,
     },
+    "TINKER_API_KEY": {
+        "description": "Tinker API key for RL training",
+        "prompt": "Tinker API key",
+        "url": "https://tinker-console.thinkingmachines.ai/keys",
+        "tools": ["rl_start_training", "rl_check_status", "rl_stop_training"],
+        "password": True,
+    },
+    "WANDB_API_KEY": {
+        "description": "Weights & Biases API key for experiment tracking",
+        "prompt": "WandB API key",
+        "url": "https://wandb.ai/authorize",
+        "tools": ["rl_get_results", "rl_check_status"],
+        "password": True,
+    },
     "OPENAI_BASE_URL": {
         "description": "Custom OpenAI-compatible API endpoint URL",
         "prompt": "API base URL (e.g., https://api.example.com/v1)",