fix(task-25): page_setup_truth and settings_pdf_mediabox_a3 move the sheet to ANSI B before proving A3

A fresh Layout1 is already ISO A3 landscape (ezdxf R2018 default: 420 x 297,
plot_rotation 0), so an A3-only /MediaBox read-back passed with
page_setup_apply stubbed to a no-op: the A/B gate row and the v4 matrix task
could not fail on the setter. Both now apply ANSI B (432 x 279, a size no
fresh document has; spec section 9 names it) and read that PDF first, then
apply ISO A3, read its PDF, and require the setter's changed.size_mm to have
moved from B to A3. The stub fails at the first PDF.

The moved-sheet comparison is +/-0.5 mm, the spec's tolerance, not exact:
measured live on AutoCAD 2026 (scratch Documents.Add(), closed unsaved), the
COM engine reports ANSI B as 431.8 x 279.4 and the DWG To PDF.pc3 file's
MediaBox as 431.8 x 279.4 then 420.158 x 297.039 for A3; the task passes
there with changed.size_mm [[431.8, 279.4], [420.0, 297.0]]. Headless it is
[[432.0, 279.0], [420.0, 297.0]].

tests/test_benchmark_v4.py gains the mutation test the finding describes
(setter stubbed -> both rows must fail; both passed on the old code) and a
run of the gate row itself; the headless task test asserts the B stage.
README rows and the tasks_v4 docstring say what the task now does; the README
collected-tests figure follows the two new tests (3282 -> 3284). The
regenerated A/B report against v1.5.1 is byte-identical (26 -> 32/32).

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01FKFStjEFzpGyLq5bMpWxTd

README.md

@@ -27,7 +27,7 @@ Live through COM on Windows, or headless through ezdxf anywhere — one typed co
 
 </div>
 
-> **v1.5 release snapshot:** 204 tools · 8 resources · 5 prompt templates · 3282 collected tests.
+> **v1.5 release snapshot:** 204 tools · 8 resources · 5 prompt templates · 3284 collected tests.
 > 204 is the **registered** count; a default install advertises 199 over `tools/list`,
 > because `ENABLE_3D` is unset. `system_about` is the runtime authority.
 
@@ -176,7 +176,7 @@ An earlier matrix scored this server 10/10, which carried no information: every
 | `selection_filter` | window 1, crossing 2, bounding box 3, polygon 1 |
 | `measure_from_handle` | 139.2699 against the 100.0 a vertex shoelace gives |
 | `pid_roundtrip` | the example sheet drawn by `pid_from_spec`, read back by `pid_graph`, which never sees the spec: 5 nodes, 4 edges, 0 dangling, `confidence_min` 1.0, `FIC-101` wired to `FCV-101` |
-| `page_setup_truth` | ISO A3 landscape applied to Layout1, plotted through `batch_plot`, and the sheet read back from the PDF's `/MediaBox`: 420 × 297 mm, not the setter's return value |
+| `page_setup_truth` | ANSI B then ISO A3 landscape applied to Layout1, each plotted through `batch_plot` and read back from its PDF's `/MediaBox`: 432 × 279 then 420 × 297 mm, not the setter's return value (a fresh layout is already A3, so the B sheet is what a no-op setter cannot fake) |
 
 ### Headless performance
 

benchmarks/README.md

@@ -95,7 +95,7 @@ fail on their own:
 | Task | Category | Verified against |
 |---|---|---|
 | `pid_roundtrip` | pid | the example spec drawn through `pid_from_spec`'s code, then read back by the graph builder, which never sees the spec: 5 nodes, 4 edges, 0 dangling ends, `confidence_min` 1.0, zero critique issues, an instrument index of exactly `FIC-101` wired to `FCV-101`, and the two authored line numbers back on the two process lines while the two unnumbered lines carry sequence-built numbers from XDATA |
-| `page_setup_truth` | pagesetup | `page_setup_apply("Layout1", ISO_A3 landscape 1:1)` then `batch_plot`; the PDF's own `/MediaBox` must parse to 420 × 297 mm (±0.5), the page-setup list must say `ISO_A3` / `landscape` / `[420, 297]`, and the ctb must be a known one |
+| `page_setup_truth` | pagesetup | `page_setup_apply("Layout1", ANSI_B landscape 1:1)` then `batch_plot` — the PDF's own `/MediaBox` must parse to 432 × 279 mm (±0.5), a size no fresh document has; then `page_setup_apply("Layout1", ISO_A3 landscape 1:1)` and `batch_plot` again — 420 × 297, the setter's `changed.size_mm` must read `[[432, 279], [420, 297]]`, the page-setup list must say `ISO_A3` / `landscape` / `[420, 297]`, and the ctb must be a known one. A setter that writes nothing fails at the first PDF (`tests/test_benchmark_v4.py` stubs it to prove that) |
 
 The competitor reports carry no result for either, for the same reason they
 carry none for the v3 five. `--matrix v3` reproduces the v1.5 set exactly.

benchmarks/adapters/autocad_mcp_pro.py

@@ -438,10 +438,29 @@ class AutoCADMCPProAdapter(BenchmarkAdapter):
         setter's ``applied`` block is what we asked for, the page-setup list is
         what the LAYOUT now says, and the PDF is what a printer would get. All
         three have to agree with ISO 216's 420 × 297.
+
+        A fresh document's Layout1 is already A3 landscape, so that read-back
+        alone would pass with the setter stubbed out. The task first moves the
+        sheet to ANSI B — 432 × 279, a size no fresh document has — and reads
+        that PDF, then applies A3 and requires the setter to report the layout
+        moved from B to A3. The stub fails at the first PDF.
         """
         from engineering.standards.papers import resolve_page_setup
         from engineering.standards.plot import batch_plot
 
+        out_dir = self.artifact_dir / "page_setup_truth"
+        out_dir.mkdir(parents=True, exist_ok=True)
+        # Stage 1: a non-default sheet, proven by its PDF.
+        await self.backend.page_setup_apply(
+            "Layout1",
+            resolve_page_setup("ANSI_B", orientation="landscape", scale="1:1"),
+        )
+        before = await batch_plot(
+            self.backend, ["Layout1"], str(out_dir), "{drawing}-{layout}-ansi_b.pdf"
+        )
+        row_before = before["sheets"][0]
+        width_before, height_before = (float(v) for v in row_before["mediabox_mm"])
+        # Stage 2: the sheet under test.
         setup = resolve_page_setup(
             "ISO_A3",
             orientation="landscape",
@@ -450,15 +469,29 @@ class AutoCADMCPProAdapter(BenchmarkAdapter):
         )
         applied = await self.backend.page_setup_apply("Layout1", setup)
         listed = (await self.backend.page_setup_list("Layout1"))[0]
-        out_dir = self.artifact_dir / "page_setup_truth"
-        out_dir.mkdir(parents=True, exist_ok=True)
-        report = await batch_plot(self.backend, ["Layout1"], str(out_dir), "{drawing}-{layout}.pdf")
+        report = await batch_plot(
+            self.backend, ["Layout1"], str(out_dir), "{drawing}-{layout}-iso_a3.pdf"
+        )
         row = report["sheets"][0]
         width_mm, height_mm = (float(v) for v in row["mediabox_mm"])
         size_listed = tuple(float(v) for v in listed["size_mm"])
+        size_changed = applied["changed"].get("size_mm")
+        # ±0.5 mm, the spec's own tolerance: the live engine measures ANSI B
+        # as 431.8 × 279.4 (11 × 17 in), the headless one as 432 × 279.
+        moved = size_changed or [[0.0, 0.0], [0.0, 0.0]]
+        moved_from_b = (
+            abs(float(moved[0][0]) - 432.0) < 0.5 and abs(float(moved[0][1]) - 279.0) < 0.5
+        )
+        moved_to_a3 = (
+            abs(float(moved[1][0]) - 420.0) < 0.5 and abs(float(moved[1][1]) - 297.0) < 0.5
+        )
         passed = (
-            applied["ok"] is True
+            abs(width_before - 432.0) < 0.5
+            and abs(height_before - 279.0) < 0.5
+            and applied["ok"] is True
             and applied["plot_style_known"] is True
+            and moved_from_b
+            and moved_to_a3
             and listed["paper"] == "ISO_A3"
             and listed["orientation"] == "landscape"
             and size_listed == (420.0, 297.0)
@@ -473,10 +506,12 @@ class AutoCADMCPProAdapter(BenchmarkAdapter):
                 "orientation": listed["orientation"],
                 "size_mm_listed": list(size_listed),
                 "mediabox_mm": [width_mm, height_mm],
+                "mediabox_mm_before": [width_before, height_before],
+                "size_mm_changed": size_changed,
                 "pdf_bytes": row["bytes"],
                 "plot_style_known": applied["plot_style_known"],
             },
-            [str(row["path"])],
+            [str(row_before["path"]), str(row["path"])],
         )
 
     async def _task_auditable_delivery(self):

benchmarks/correctness_suite.py

@@ -376,17 +376,45 @@ async def settings_layer_state_roundtrip():
     )
 
 
+def _sheet_near(size_mm, width_mm: float, height_mm: float) -> bool:
+    """Within the spec's ±0.5 mm: COM measures ANSI B as 431.8 × 279.4."""
+    try:
+        w, h = (float(v) for v in size_mm)
+    except (TypeError, ValueError):
+        return False
+    return abs(w - width_mm) < 0.5 and abs(h - height_mm) < 0.5
+
+
 async def settings_pdf_mediabox_a3():
-    """Page setup evidence is the PDF's own /MediaBox (spec §8.3)."""
+    """Page setup evidence is the PDF's own /MediaBox (spec §8.3).
+
+    A fresh document's Layout1 is already ISO A3 landscape, so an A3-only
+    read-back would pass with the setter stubbed out. The sheet is therefore
+    moved to ANSI B first — 432 × 279, a size no fresh document has (spec §9
+    names it) — and that PDF is read; then ISO A3 is applied and read again.
+    The A3 apply must also report the layout moved from B to A3, so the PDF
+    and the setter's own diff have to agree on where the sheet was.
+    """
     from engineering.standards.papers import resolve_page_setup
     from engineering.standards.plot import batch_plot
 
     b = await _b()
-    await b.page_setup_apply("Layout1", resolve_page_setup("ISO_A3"))
+    await b.page_setup_apply("Layout1", resolve_page_setup("ANSI_B"))
     out_dir = tempfile.mkdtemp()
-    report = await batch_plot(b, ["Layout1"], out_dir, "{drawing}-{layout}.pdf")
-    width_mm, height_mm = report["sheets"][0]["mediabox_mm"]
-    return abs(width_mm - 420.0) < 0.5 and abs(height_mm - 297.0) < 0.5
+    report_b = await batch_plot(b, ["Layout1"], out_dir, "{drawing}-{layout}-ansi_b.pdf")
+    width_b, height_b = report_b["sheets"][0]["mediabox_mm"]
+    applied = await b.page_setup_apply("Layout1", resolve_page_setup("ISO_A3"))
+    report_a3 = await batch_plot(b, ["Layout1"], out_dir, "{drawing}-{layout}-iso_a3.pdf")
+    width_a3, height_a3 = report_a3["sheets"][0]["mediabox_mm"]
+    moved = applied["changed"].get("size_mm") or [[0.0, 0.0], [0.0, 0.0]]
+    return (
+        abs(width_b - 432.0) < 0.5
+        and abs(height_b - 279.0) < 0.5
+        and _sheet_near(moved[0], 432.0, 279.0)
+        and _sheet_near(moved[1], 420.0, 297.0)
+        and abs(width_a3 - 420.0) < 0.5
+        and abs(height_a3 - 297.0) < 0.5
+    )
 
 
 CHECKS = {

benchmarks/tasks_v4.py

@@ -7,7 +7,9 @@ and the instrument index are each derived independently of the drawing code.
 ``page_setup_truth`` (track E) applies an ISO A3 landscape page setup to a
 layout, plots it through ``batch_plot`` and reads the sheet size back from
 the PDF's own ``/MediaBox`` — the setup is verified by the file, not by the
-setter's return value.
+setter's return value. A fresh Layout1 is already A3 landscape, so the task
+moves the sheet to ANSI B (432 × 279) and reads that PDF first; a setter that
+writes nothing fails there, not at the A3 read-back.
 
 The published competitor reports were never asked either question; the chart
 shows ``not_run`` for them, not zero.

tests/test_benchmark_v4.py

@@ -67,3 +67,58 @@ async def test_page_setup_truth_passes_headlessly(tmp_path):
     assert passed, metrics
     assert abs(metrics["mediabox_mm"][0] - 420.0) < 0.5
     assert abs(metrics["mediabox_mm"][1] - 297.0) < 0.5
+    # The stage that makes the task falsifiable: the sheet was ANSI B first.
+    assert abs(metrics["mediabox_mm_before"][0] - 432.0) < 0.5
+    assert abs(metrics["mediabox_mm_before"][1] - 279.0) < 0.5
+    assert metrics["size_mm_changed"] == [[432.0, 279.0], [420.0, 297.0]]
+
+
+async def _noop_page_setup_apply(self, layout, setup):
+    """A setter that writes nothing and claims success."""
+    return {
+        "ok": True,
+        "layout": layout,
+        "applied": dict(setup),
+        "changed": {},
+        "warnings": [],
+        "plot_style_known": True,
+        "viewports_kept": True,
+        "backend": "ezdxf",
+    }
+
+
+@pytest.mark.asyncio
+async def test_page_setup_truth_fails_when_the_setter_writes_nothing(tmp_path, monkeypatch):
+    """A fresh Layout1 is already ISO A3 landscape (ezdxf's R2018 default: 420 x 297,
+    rotation 0), so a task that only reads A3 back from the PDF cannot tell a
+    working setter from a stub. Both gate rows must fail with the stub."""
+    pytest.importorskip("matplotlib", reason="rendering needs the [pdf] extra")
+    from backends.ezdxf_backend import EzdxfBackend
+    from benchmarks import correctness_suite
+    from benchmarks.adapters.autocad_mcp_pro import AutoCADMCPProAdapter
+
+    monkeypatch.setattr(EzdxfBackend, "page_setup_apply", _noop_page_setup_apply)
+
+    assert await correctness_suite.settings_pdf_mediabox_a3() is False
+
+    adapter = AutoCADMCPProAdapter(backend="ezdxf")
+    await adapter.setup(tmp_path)
+    try:
+        await adapter._reset()
+        passed, metrics, _artifacts = await adapter._task_page_setup_truth()
+    finally:
+        await adapter.cleanup()
+    assert passed is False, metrics
+    # The stub's own evidence: the "ANSI B" PDF is still the default A3 sheet.
+    assert abs(metrics["mediabox_mm_before"][0] - 420.0) < 0.5
+    assert metrics["size_mm_changed"] is None
+
+
+@pytest.mark.asyncio
+async def test_correctness_check_settings_pdf_mediabox_a3_passes():
+    """The A/B gate row itself, run once here: ANSI B plotted at 432 x 279,
+    then ISO A3 at 420 x 297, each read from its own PDF."""
+    pytest.importorskip("matplotlib", reason="rendering needs the [pdf] extra")
+    from benchmarks import correctness_suite
+
+    assert await correctness_suite.settings_pdf_mediabox_a3() is True