llm-anthropic 0.25 Adds Opus 4.7 with xhigh Thinking Effort
The llm-anthropic CLI tool has been updated to version 0.25, adding support for the new Claude Opus 4.7 model with an 'xhigh' thinking effort setting for complex coding tasks.
Why it matters
This update gives developers direct access to Claude's most powerful reasoning abilities through a simple CLI tool, enabling them to tackle their most challenging coding tasks.
Key Points
- 1New Claude Opus 4.7 model with 'xhigh' thinking effort setting
- 2Added 'thinking_display' and 'thinking_adaptive' flags for better control
- 3Increased default 'max_tokens' to the maximum allowed for each model
- 4Removed obsolete 'structured-outputs-2025-11-13' beta header
Details
The llm-anthropic tool, which allows developers to run Anthropic's Claude language models locally, has been updated to version 0.25. The key change is the addition of the new Claude Opus 4.7 model, which introduces a new 'xhigh' thinking effort setting. This setting enables Claude's deepest reasoning capabilities, allowing it to tackle the most complex coding problems such as refactoring, debugging, and system design. The update also includes new flags like 'thinking_display' and 'thinking_adaptive' to provide more control over the model's behavior. Additionally, the default 'max_tokens' value has been increased to the maximum allowed for each model, and an obsolete beta header has been removed.
No comments yet
Be the first to comment