Update command flag handling

`lmcli chat` now supports common prompt flags (model, length, system
prompt, etc)

pkg/cmd/prompt.go

@@ -22,21 +22,23 @@ func PromptCmd(ctx *lmcli.Context) *cobra.Command {
 
 			messages := []model.Message{
 				{
-					Role:            model.MessageRoleSystem,
-					Content: getSystemPrompt(ctx),
+					Role:    model.MessageRoleSystem,
+					Content: ctx.GetSystemPrompt(),
 				},
 				{
-					Role:            model.MessageRoleUser,
+					Role:    model.MessageRoleUser,
 					Content: message,
 				},
 			}
 
-			_, err := cmdutil.FetchAndShowCompletion(ctx, messages, nil)
+			_, err := cmdutil.Prompt(ctx, messages, nil)
 			if err != nil {
 				return fmt.Errorf("Error fetching LLM response: %v", err)
 			}
 			return nil
 		},
 	}
+
+	applyPromptFlags(ctx, cmd)
 	return cmd
 }