Check page band legends against bands.py; amber is verified, not sampled

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

rpa-dashboard-ai/templates/web/bands.py

@@ -5,14 +5,17 @@ an exported sheet, the approve gate) imports from here, so they never disagree
 about what counts as red.
 
     GREEN  >= 0.95   clean print, straight through
-    AMBER  0.90-0.95 slightly unclear, sampled
+    AMBER  0.90-0.95 slightly unclear, check it
-    RED    <  0.90   handwriting or a messy scan, always reviewed
+    RED    <  0.90   handwriting or a messy scan
-    BLANK            a mandatory field with no value, always flagged
+    BLANK            a mandatory field with no value
     UNSCORED         no word scores came back for the value
 
+The approve gate: every field that isn't green must be verified by a person before the
+run can be approved (needs_review). Amber is not sampled; it is checked like red.
+
 Calibration (from the prototype these rules came from): crisp print scored 0.90 and
 up, handwriting clustered in 0.80-0.89, and 0.70-0.79 was empty. 0.90 sits in that
-gap. 0.95 splits off the 0.90-0.99 band that reviewers sample rather than trust.
+gap. 0.95 splits off the slightly unclear 0.90-0.95 reads from clean print.
 
 What a band claims: the score is the model's own legibility rating. Green means the
 text was read cleanly, NOT that the value is correct; a confident misread scores

rpa-dashboard-ai/templates/web/server_stub.py

@@ -22,7 +22,7 @@ from pricing import PRICING_AS_OF, PRICING_SOURCE, cost_for_call
 
 HERE = Path(__file__).resolve().parent
 API = "/api"  # same as API_BASE in index.html
-REASON = {"green": None, "amber": "Slightly unclear, sample check", "red": "Unclear print, check every word",
+REASON = {"green": None, "amber": "Slightly unclear, verify it", "red": "Unclear print, check every word",
           "blank": "Required field is empty", "unscored": "Not found in the transcription"}
 # (field, value, word scores, mandatory). Swap in the fields the project's extraction returns.
 SAMPLE_FIELDS = [

tests/test_bands.py

@@ -1,5 +1,6 @@
 """Confidence bands: thresholds, the worst-word rule and the blank-mandatory flag (spec: Banding)."""
 import importlib.util
+import re
 from pathlib import Path
 
 BANDS = Path(__file__).resolve().parents[1] / "rpa-dashboard-ai" / "templates" / "web" / "bands.py"
@@ -39,3 +40,13 @@ def test_no_scores_means_unscored():
 def test_only_green_skips_review():
     assert not bands.needs_review("green")
     assert all(bands.needs_review(b) for b in ["amber", "red", "blank", "unscored"])
+
+
+def test_page_legends_use_the_bands_py_cut_points():
+    """The legend labels are hard-coded in the pages; they must say what bands.py decides."""
+    green, floor = bands.GREEN_THRESHOLD, bands.CONFIDENCE_THRESHOLD
+    for page in [BANDS.parents[1] / "web" / "src" / "ai.ts", BANDS.parents[1] / "desktop" / "ai_sections.html"]:
+        m = re.search(r"Clean ≥([\d.]+).*?Check ([\d.]+)–([\d.]+).*?Review <([\d.]+)",
+                      page.read_text(encoding="utf-8"), re.S)
+        assert m, f"{page.name}: band legend labels not found"
+        assert tuple(map(float, m.groups())) == (green, floor, green, floor), page.name