Provides summarised output from various actions that could otherwise eat up tokens and cause crashes.
API key for the selected provider.
AI provider to use. Supported values: ANTHROPIC, OPENAI, OPENAI-COMPATIBLE, GOOGLE.
Specific model to use.
Maximum tokens for model responses.
Fallback directory for trying to find files with relative paths from.
Custom API endpoint for OpenAI-compatible providers.
Cache duration in milliseconds.
Character count threshold for when to summarize.