feat: switch default Ollama model to gemma4:e2b

gemma4:e2b has native function calling with dedicated tool tokens,
achieving 100% tool selection accuracy in benchmarks vs 67% for
mistral-nemo-large, with 5-8x faster response times (2-4s vs 15-20s)
and lower VRAM usage (8GB vs 9.2GB).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

src/core/config.py

@@ -84,7 +84,7 @@ class Config(BaseSettings):
         description="Ollama server URL"
     )
     OLLAMA_DEFAULT_MODEL: str = Field(
-        default="mistral-nemo:latest",
+        default="gemma4:e2b",
         description="Default Ollama model"
     )
     OLLAMA_TIMEOUT: int = Field(