Fix openai_completion tests for ollama

When called via the OpenAI API, ollama is responding with more brief
responses than when called via its native API. This adjusts the
prompting for its OpenAI calls to ask it to be more verbose.

llama_stack/providers/remote/inference/ollama/ollama.py

@@ -348,6 +348,9 @@ class OllamaInferenceAdapter(
         top_p: Optional[float] = None,
         user: Optional[str] = None,
     ) -> OpenAICompletion:
+        if not isinstance(prompt, str):
+            raise ValueError("Ollama does not support non-string prompts for completion")
+
         model_obj = await self._get_model(model)
         params = {
             k: v