Categorize tools into 'model capabilities categories' to help determine which type of model to pick when in auto mode

Encourage Claude to pick the best model for the job automatically in auto mode
Lots of new tests to ensure automatic model picking works reliably based on user preference or when a matching model is not found or ambiguous
Improved error reporting when bogus model is requested and is not configured or available

tools/models.py

@@ -2,11 +2,20 @@
 Data models for tool responses and interactions
 """
 
+from enum import Enum
 from typing import Any, Literal, Optional
 
 from pydantic import BaseModel, Field
 
 
+class ToolModelCategory(Enum):
+    """Categories for tool model selection based on requirements."""
+
+    EXTENDED_REASONING = "extended_reasoning"  # Requires deep thinking capabilities
+    FAST_RESPONSE = "fast_response"  # Speed and cost efficiency preferred
+    BALANCED = "balanced"  # Balance of capability and performance
+
+
 class ContinuationOffer(BaseModel):
     """Offer for Claude to continue conversation when Gemini doesn't ask follow-up"""