diff --git a/vision.py b/vision.py
index f02dec0..0481e44 100644
--- a/vision.py
+++ b/vision.py
@@ -692,6 +692,15 @@ centering, that range should be genuinely wide (e.g. 6-9), not cosmetic.
 where you could assess all four categories; "medium" when one or two \
 categories are unassessable; "low" when the photo mainly supports identifying \
 the card rather than grading it.
+  Centering and edge whitening are measured directly from the pixels when a \
+MEASURED CENTERING / MEASURED EDGE WHITENING block is supplied above — that's \
+a materially stronger basis than reading either by eye, and the reverse is \
+true too: if NEITHER was measurable on this card (both missing or refused, \
+with a reason given), don't call this "high" even if the photo itself is \
+sharp and well-lit. A crisp photo of a card whose finish defeats the \
+measurement (foil, refractor, die-cut, or the margin problem described \
+above) still leaves you assessing two of the four categories by eye alone, \
+which is exactly what "medium" is for.
 - limitations: list each specific thing the photo prevented you from checking \
 ("back not shown, so back centering and back corners are unknown", "resolution \
 too low to see print lines or light surface scratches").
@@ -993,6 +1002,32 @@ def grade_card(images, api_key=None, model=None, effort=None, zoom_details=True)
     if card_type not in ("pokemon", "sports", "other_tcg", "other"):
         card_type = "other"
 
+    confidence = parsed.get("confidence") or "low"
+    limitations = [l for l in (parsed.get("limitations") or []) if l]
+
+    # "high" confidence is defined to the model as being able to confidently
+    # assess all four categories — but centering and edge whitening are the
+    # two this app can measure from pixels rather than ask the model to
+    # judge by eye, and a self-reported "high" doesn't reliably account for
+    # whether that measurement was actually available on THIS card. Capped
+    # here rather than left to the prompt alone: the model juggles a long
+    # instruction list already, and this is exactly the kind of objective,
+    # checkable fact code should enforce rather than hope gets weighed
+    # correctly every time. Only caps a "high" claim down to "medium" when
+    # NEITHER was measured — one of two still measured is a real basis the
+    # model may legitimately be confident from, so that's left to its own
+    # judgment.
+    def _measured_ok(m):
+        return bool(m) and m.get("reliable", True) is not False
+
+    if confidence == "high" and not _measured_ok(centering) and not _measured_ok(measured):
+        confidence = "medium"
+        limitations.append(
+            "Confidence capped at medium: neither centering nor edge "
+            "whitening could be measured from the pixels on this photo, so "
+            "the estimate leans on the photo alone for two of PSA's four "
+            "categories rather than a direct pixel measurement for either.")
+
     return {
         "closeups": len(crops),
         "card_type": card_type,
@@ -1004,14 +1039,14 @@ def grade_card(images, api_key=None, model=None, effort=None, zoom_details=True)
         "estimated_grade": _clean_grade(parsed.get("estimated_grade")),
         "grade_low": low,
         "grade_high": high,
-        "confidence": parsed.get("confidence") or "low",
+        "confidence": confidence,
         "categories": {
             "centering": _clean_category(parsed.get("centering")),
             "corners": _clean_category(parsed.get("corners")),
             "edges": _clean_category(parsed.get("edges")),
             "surface": _clean_category(parsed.get("surface")),
         },
-        "limitations": [l for l in (parsed.get("limitations") or []) if l],
+        "limitations": limitations,
         "note": parsed.get("note") or "",
         "usage": usage,
     }