Enhance BatchRunner and AIAgent with new configuration options, default model now opus 4.6, default summarizer gemini flash 3

- Added `max_tokens`, `reasoning_config`, and `prefill_messages` parameters to `BatchRunner` and `AIAgent` for improved model response control.
- Updated CLI to support new options for reasoning effort and prefill messages from a JSON file.
- Modified example configuration files to reflect changes in default model and summary model.
- Improved error handling for loading prefill messages and reasoning configurations in the CLI.
- Updated documentation to include new parameters and usage examples.

gateway/run.py

@@ -481,7 +481,7 @@ class GatewayRunner:
             max_iterations = int(os.getenv("HERMES_MAX_ITERATIONS", "60"))
             
             agent = AIAgent(
-                model=os.getenv("HERMES_MODEL", "anthropic/claude-sonnet-4"),
+                model=os.getenv("HERMES_MODEL", "anthropic/claude-opus-4.6"),
                 max_iterations=max_iterations,
                 quiet_mode=True,
                 enabled_toolsets=[toolset],