fix: prevent panic when LLMAgent has no Model configured (google#280)

Add nil check in Flow.callLLM() after BeforeModelCallbacks but before
accessing Model.GenerateContent(). This prevents a nil pointer dereference
panic when an llmagent is created without a Model configuration.

The check is positioned after BeforeModelCallbacks to allow callbacks that
return cached responses to short-circuit execution without requiring a Model.

This provides a clear error message instead of a cryptic segmentation fault:
'agent %q has no Model configured; ensure Model is set in llmagent.Config'

Preserves valid use cases:
- Testing agent metadata/structure without running the agent
- BeforeAgentCallbacks that short-circuit before agent execution
- BeforeModelCallbacks that return cached responses

Fixes panic: runtime error: invalid memory address or nil pointer
dereference when sub-agents without Models were invoked.

Author: apzuk3

internal/llminternal/base_flow.go

@@ -248,6 +248,11 @@ func (f *Flow) callLLM(ctx agent.InvocationContext, req *model.LLMRequest, state
 			}
 		}
 
+		if f.Model == nil {
+			yield(nil, fmt.Errorf("agent %q has no Model configured; ensure Model is set in llmagent.Config", ctx.Agent().Name()))
+			return
+		}
+
 		// TODO: Set _ADK_AGENT_NAME_LABEL_KEY in req.GenerateConfig.Labels
 		// to help with slicing the billing reports on a per-agent basis.