fix: prevent infinite whitespace in grammar rules

Fixes #93

The whitespace rule `ws ::= ([ \t\n]+)` allows unlimited consecutive
whitespace characters. At higher temperatures (e.g., 0.8), this can cause
the model to generate endless tabs/spaces, resulting in:
- Token exhaustion
- Invalid JSON output
- ~10% failure rate in function calling

Changed to `ws ::= ([ \t\n]?)` which:
- Allows zero or one whitespace character
- Prevents infinite loops while maintaining JSON validity
- More restrictive than `{1}` (allows optional whitespace)

Tested with Mistral 7B Instruct v0.2.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

Author: awanawona

src/llama_cpp_agent/gbnf_grammar_generator/gbnf_grammar_from_pydantic_models.py

@@ -802,7 +802,7 @@ def get_primitive_grammar(grammar):
         [^"\\] |
         "\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
       )* "\""
-ws ::= ([ \t\n]+)
+ws ::= ([ \t\n]?)
 number ::= "-"? ([0-9]+ | [0-9]+ "." [0-9]+) ([eE] [-+]? [0-9]+)?"""
 
     any_block = ""