feat: add grok to TOOL_USE_ENFORCEMENT_MODELS for direct xAI usage (#5595)

Grok models (x-ai/grok-4.20-beta, grok-code-fast-1) now receive tool-use
enforcement guidance, steering them to actually call tools instead of
describing intended actions. Matches both OpenRouter (x-ai/grok-*) and
direct xAI API usage.

tests/agent/test_prompt_builder.py

@@ -1018,6 +1018,9 @@ class TestToolUseEnforcementGuidance:
     def test_enforcement_models_includes_codex(self):
         assert "codex" in TOOL_USE_ENFORCEMENT_MODELS
 
+    def test_enforcement_models_includes_grok(self):
+        assert "grok" in TOOL_USE_ENFORCEMENT_MODELS
+
     def test_enforcement_models_is_tuple(self):
         assert isinstance(TOOL_USE_ENFORCEMENT_MODELS, tuple)