feat: coverage ladder + vision-unverified stamping (classic path)

tests/test_extraction_ladder_classic.py

@@ -0,0 +1,98 @@
+"""Coverage-driven extraction retry ladder — classic path (pipeline/extractor.py)."""
+
+from backend import config
+from backend.pipeline import extractor
+
+PAGE_TEXT = ("1. \nALL SAWN LUMBER IN CONTACT WITH SOIL TO BE SOUTHERN PINE, "
+             "PRESSURE TREATED.\n2. \nROOF SHEATHING: 5/8\" PLYWOOD, C-D GRADE, "
+             "STRUCTURAL I.")
+
+
+def _page(n=8, text=PAGE_TEXT):
+    return {"page_number": n, "base64": "AAAA", "text_layer": text}
+
+
+def test_classic_fallback_when_vision_returns_nothing(monkeypatch):
+    """Vision pass returns an unusable bare list; text retry disabled ->
+    deterministic fallback stubs make a dark sheet impossible."""
+    monkeypatch.setattr(extractor, "call_json",
+                        lambda **kw: [{"name": "general notes", "value": "notes"}])
+    monkeypatch.setattr(config, "EXTRACT_TEXT_RETRY_ENABLED", False)
+    sheet = extractor._extract_one(_page())
+    assert sheet["assertions"], "dark sheet must be impossible with fallback enabled"
+    assert all(a.get("grounding") == "text_layer_fallback"
+               for a in sheet["assertions"])
+    assert sheet["coverage"]["ratio"] >= 0.6
+
+
+def test_classic_merge_preserves_graphical_objects(monkeypatch):
+    """Rung-2 merge must never drop vision-only graphical objects."""
+    def fake(**kw):
+        if kw.get("images_b64"):
+            return {"sheet": {}, "objects": [
+                {"object_id": "g1", "object_type": "lighting_fixture",
+                 "name": "pendant at grid C-4", "source_text": None,
+                 "graphical_basis": "16in pendant symbol at grid C-4"}]}
+        return {"sheet": {}, "objects": [
+            {"object_id": "t1", "object_type": "general_note",
+             "source_text": "ALL SAWN LUMBER IN CONTACT WITH SOIL TO BE "
+                            "SOUTHERN PINE, PRESSURE TREATED.",
+             "name": "lumber note"}]}
+
+    monkeypatch.setattr(extractor, "call_json", fake)
+    sheet = extractor._extract_one(_page())
+    assert any(a.get("graphical_basis") for a in sheet["assertions"])
+    assert any("SAWN LUMBER" in (a.get("source_text") or "")
+               for a in sheet["assertions"])
+
+
+def test_classic_recovers_sheet_number(monkeypatch):
+    text = ("REFLECTED CEILING PLAN\n"
+            "GYP. BD. CEILING 8'-11 3/8\" A.F.F. TYP. FOR ALL STOREFRONT\n"
+            "LED TAPE LIGHT. SEE ELEC. SCONCE 8'-0\" A.F.F., SEE ELEC.\n"
+            "A102")
+
+    def fake(**kw):
+        if kw.get("images_b64"):
+            return {"sheet": {}, "objects": [
+                {"object_id": "o1", "name": "RCP ceiling note",
+                 "source_text": "GYP. BD. CEILING 8'-11 3/8\" A.F.F. TYP. "
+                                "FOR ALL STOREFRONT",
+                 "attributes": {"height": "8'-11 3/8\""}}]}
+        return {"sheet": {}, "objects": []}
+
+    monkeypatch.setattr(extractor, "call_json", fake)
+    sheet = extractor._extract_one(_page(18, text))
+    assert sheet["sheet_number"] == "A102"
+
+
+def test_classic_skips_retry_when_coverage_healthy(monkeypatch):
+    calls = []
+
+    def fake(**kw):
+        calls.append(kw)
+        return {"sheet": {"sheet_number": "S202"}, "objects": [
+            {"object_id": "o1", "name": "lumber note",
+             "source_text": "ALL SAWN LUMBER IN CONTACT WITH SOIL TO BE "
+                            "SOUTHERN PINE, PRESSURE TREATED.",
+             "attributes": {"species": "southern pine"}},
+            {"object_id": "o2", "name": "sheathing note",
+             "source_text": "ROOF SHEATHING: 5/8\" PLYWOOD, C-D GRADE, "
+                            "STRUCTURAL I.",
+             "attributes": {"sheathing": "5/8 plywood"}}]}
+
+    monkeypatch.setattr(extractor, "call_json", fake)
+    sheet = extractor._extract_one(_page())
+    assert len(calls) == 1, "healthy coverage must not trigger the text-only rung"
+    assert sheet["coverage"]["ratio"] == 1.0
+    assert sheet["sheet_number"] == "S202"
+
+
+def test_classic_scanned_page_keeps_failed_sheet_shape(monkeypatch):
+    """No text layer (scanned page): total parse failure keeps the existing
+    'extraction failed' empty-sheet return — ladder is text-layer-only."""
+    monkeypatch.setattr(extractor, "call_json", lambda **kw: None)
+    sheet = extractor._extract_one({"page_number": 4, "base64": "AAAA",
+                                    "text_layer": None})
+    assert sheet["assertions"] == []
+    assert "extraction failed" in (sheet.get("sheet_title") or "")

tests/test_extractor_text_grounding.py

@@ -84,3 +84,39 @@ def test_extractor_instruction_fully_substituted():
     out = (EXTRACTOR_USER_INSTRUCTION.replace("{sheet_hint}", "")
            + _text_layer_block(page))
     assert "{sheet_hint}" not in out
+
+
+def test_vision_unverified_stamp_when_source_text_not_in_text_layer():
+    """Digits ground the object against the page text, but its quoted
+    source_text is not actually present in the text layer: kept, stamped
+    vision_unverified (the wave-5b verifier consumes grounding stamps)."""
+    page_text = "WALL: 2X6 WD STUD @ 16\" O.C. WITH R-13 BATT INSULATION"
+    parsed = {"sheet": {}, "objects": [
+        {"object_id": "x1", "name": "stud pack",
+         "source_text": "(5) 2X6 STUD PACK AT JAMB",  # NOT in page text
+         "attributes": {"count": "5"}}]}
+    sheet = _normalize_sheet(parsed, 1, page_text=page_text)
+    assert len(sheet["assertions"]) == 1
+    assert sheet["assertions"][0]["grounding"] == "vision_unverified"
+
+
+def test_no_unverified_stamp_when_source_text_in_text_layer():
+    page_text = "WALL: 2X6 WD STUD @ 16\" O.C. WITH R-13 BATT INSULATION"
+    parsed = {"sheet": {}, "objects": [
+        {"object_id": "x1", "name": "stud note",
+         "source_text": "2X6 WD STUD @ 16\" O.C.",
+         "attributes": {"size": "2x6"}}]}
+    sheet = _normalize_sheet(parsed, 1, page_text=page_text)
+    assert len(sheet["assertions"]) == 1
+    assert "grounding" not in sheet["assertions"][0]
+
+
+def test_preset_grounding_stamp_survives_normalization():
+    """Fallback/merge rungs stamp grounding upstream; normalization must
+    preserve a pre-set stamp instead of recomputing it away."""
+    parsed = {"sheet": {}, "objects": [
+        {"object_id": "f1", "name": "lumber note",
+         "source_text": "ALL LUMBER SOUTHERN PINE",
+         "grounding": "text_layer_fallback"}]}
+    sheet = _normalize_sheet(parsed, 1, page_text="ALL LUMBER SOUTHERN PINE")
+    assert sheet["assertions"][0]["grounding"] == "text_layer_fallback"