bench: matrix v4 adds page_setup_truth; correctness suite grows to 32 with three settings checks (A/B vs v1.5.1: 26 -> 32 / 32)

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

tests/test_benchmark_v4.py

@@ -1,23 +1,28 @@
-"""Track A — the v4 task matrix.
+# tests/test_benchmark_v4.py
+"""The v4 task matrix: v3 plus what 1.6 added.
 
-v4 adds one task, ``pid_roundtrip``: draw a P&ID through the same code the
-tools call and read it back through the graph builder, so the edge count, the
-dangling count and the instrument index are each derived independently of the
-drawing code. The published competitor reports were never asked this question
-and the chart shows them ``not_run`` — the same rule v3 set for its five.
+Track A added ``pid_roundtrip``; track E adds ``page_setup_truth`` — apply an
+ISO A3 landscape page setup, plot through ``batch_plot`` and read the sheet
+size back from the PDF's own ``/MediaBox``. The published competitor reports
+were never asked either question and the chart shows them ``not_run`` — the
+same rule v3 set for its five.
 """
 
 from __future__ import annotations
 
+import pytest
+
 from benchmarks.tasks_v3 import TASKS_V3
 from benchmarks.tasks_v4 import DEFAULT_MATRIX, MATRICES, NEW_TASKS_V4, TASKS_V4, task_by_id
 
 
 def test_v4_extends_v3_without_touching_it():
     assert TASKS_V4[: len(TASKS_V3)] == TASKS_V3
-    assert [t.task_id for t in NEW_TASKS_V4] == ["pid_roundtrip"]
+    assert [t.task_id for t in NEW_TASKS_V4] == ["pid_roundtrip", "page_setup_truth"]
+    assert len(TASKS_V4) == 17
     assert MATRICES["v3"] == TASKS_V3 and MATRICES["v4"] == TASKS_V4 and DEFAULT_MATRIX == "v4"
     assert task_by_id("pid_roundtrip").category == "pid"
+    assert task_by_id("page_setup_truth").category == "pagesetup"
 
 
 def test_the_adapter_implements_every_v4_task():
@@ -32,4 +37,33 @@ def test_correctness_suite_has_the_pid_checks():
 
     for name in ("pid_block_define_attdef_roundtrip", "pid_tag_parse_fic", "pid_graph_edge_count"):
         assert CHECKS[name][1] == "P&ID"
-    assert len(CHECKS) == 29
+
+
+def test_correctness_suite_has_the_settings_checks():
+    from benchmarks.correctness_suite import CHECKS
+
+    for name in (
+        "settings_dimstyle_iso25_values",
+        "settings_layer_state_roundtrip",
+        "settings_pdf_mediabox_a3",
+    ):
+        assert CHECKS[name][1] == "Settings"
+    assert len(CHECKS) == 32
+
+
+@pytest.mark.asyncio  # asyncio_mode is strict; the four tests above are sync
+async def test_page_setup_truth_passes_headlessly(tmp_path):
+    """The benchmark task itself, run once here so a regression in page setup
+    or the PDF read-back fails the suite and not only the matrix."""
+    from benchmarks.adapters.autocad_mcp_pro import AutoCADMCPProAdapter
+
+    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, metrics
+    assert abs(metrics["mediabox_mm"][0] - 420.0) < 0.5
+    assert abs(metrics["mediabox_mm"][1] - 297.0) < 0.5