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.
This commit is contained in:
teknium 2026-02-08 10:49:24 +00:00
parent fa76a331b0
commit f12ea1bc02
7 changed files with 324 additions and 40 deletions

View file

@ -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],