EDIT - old but seems like a decent review: https://www.scientificamerican.com/article/soil-depletion-an...
To recap, there are declines up to 30% in certain nutrients for certain vegetables. This seems to be mostly down to farmers choosing varietals that grow faster and handle transport better over time.
Personally it's still my opinion that this is no big deal. Even if, say, oranges are lower-quality than a century ago, they are now cheap, easy to obtain and available year-round. You might have to eat four oranges instead of one for whatever nutrient allotment you desire but...that's a heck of a lot easier than it was for our grandparents. As long as people aren't eating mainly combinations of flour and oil, they'll be fine.
I don’t think we are at the point where it’s either nutritional deficiency or obesity, but that seems like the ultimate risk here.
And fruit is in general very good for you, but of course it's also quite high in calories. A single navel orange has upwards of 70 calories [1]. So 2 oranges ~= 1 can of Coke. And fruit juice is even worse. A plain cup of orange juice has 112 calories. If somebody buys some form of it that's been sweetened or otherwise mixed, you can easily end up with your OJ having more calories than a Coke.
People can easily speed their way to obesity by eating things that they think (and are) 'good for them' without really appreciating how many calories they're consuming. Similar to how things like vegans can easily end up consuming way too many calories when doing things like using peanuts as a protein source. An 80kg man needs around 64 grams of protein a day. 64 grams of protein from peanuts (to take things to an extreme) would be more than 1400 calories. And that's from raw unseasoned peanuts, which have the best nutrition:calorie ratio.
[1] - https://www.verywellfit.com/oranges-nutrition-facts-calories...
Roughly speaking, 100 extra calories a day means 1 added pound of fat per month.
"The apparent overall decreases for some nutrients are interesting and potentially of concern, but like Mayer and Johnson, we urge caution about their interpretation. Mineral decreases are popularly predicted for, or blamed on, mineral deficiencies in soil and fertilizer [5], but without sufficient consideration of contrary evidence and other possibilities.
[Snipping various scientific evidence they mention]
Factors other than soil mineral concentrations seem to have primary control of food mineral contents for the foods and minerals studied here. (The minerals I and Se are well known exceptions to this rule.) In the case of Fe, depletion is never an issue; instead, the issue is the ability of the plant to acquire the Fe that it needs. The fraction of soluble Fe in soils may be only about 10^-13 of total soil Fe."
In general, there seems to be an inverse relationship between nutrition and yield: higher nutrition + lower yield, or lower nutrition + higher yield. It's not hard to guess which we pick. But then the article (similar to another published in Discover magazine) focuses entirely and exclusively on soil quality as the primary issue.
[1] - https://pubmed.ncbi.nlm.nih.gov/15637215/
[2] (SciHubbed) - https://sci-hub.st/https://pubmed.ncbi.nlm.nih.gov/15637215/