test(e2e-chain): fold stress results into report_data.json

report_build.py reads stress_results.json (when --stress-results given), adds a stress block (cases + by_axis), per-axis scaling-curve PNGs, aggregate stress headline metrics, and stress regression rows vs the previous run. Degrades to no stress section when the file is absent. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-06-26 09:26:45 +02:00
parent 7bd61912af
commit ec8e5c43c3
2 changed files with 182 additions and 5 deletions
@@ -0,0 +1,63 @@
+import os
+import report_build as RB
+
+_SR = {
+    "overall": "PASS",
+    "cases": [
+        {"id": "ds_size_1000", "shape": "hub", "axis": "ds_signal_elements",
+         "level": 1000, "status": "PASS", "survival": True, "clients": 1,
+         "min_frames": 200, "marte_cpu_s": 12.8, "marte_rss_mb": 10.4,
+         "hub_cpu_s": 2.33, "hub_rss_mb": 28.3, "zoom_count": 0, "zoom_fail": 0,
+         "zoom_p50_ms": 0.0, "zoom_p95_ms": 0.0, "fails": []},
+        {"id": "ds_size_4000", "shape": "hub", "axis": "ds_signal_elements",
+         "level": 4000, "status": "PASS", "survival": True, "clients": 1,
+         "min_frames": 180, "marte_cpu_s": 20.0, "marte_rss_mb": 14.0,
+         "hub_cpu_s": 3.0, "hub_rss_mb": 40.0, "zoom_count": 0, "zoom_fail": 0,
+         "zoom_p50_ms": 0.0, "zoom_p95_ms": 0.0, "fails": []},
+        {"id": "hub_reqrate_50", "shape": "hub", "axis": "hub_zoom_reqrate_hz",
+         "level": 50, "status": "PASS", "survival": True, "clients": 4,
+         "min_frames": 100, "marte_cpu_s": 5.0, "marte_rss_mb": 12.0,
+         "hub_cpu_s": 8.0, "hub_rss_mb": 60.0, "zoom_count": 400, "zoom_fail": 0,
+         "zoom_p50_ms": 12.0, "zoom_p95_ms": 35.0, "fails": []},
+    ],
+}
+
+
+def test_build_stress_groups_by_axis_sorted_by_level():
+    st = RB.build_stress(_SR)
+    assert st["overall"] == "PASS"
+    assert len(st["cases"]) == 3
+    assert set(st["by_axis"]) == {"ds_signal_elements", "hub_zoom_reqrate_hz"}
+    levels = [c["level"] for c in st["by_axis"]["ds_signal_elements"]]
+    assert levels == [1000, 4000]  # sorted ascending
+
+
+def test_stress_headline_aggregates():
+    st = RB.build_stress(_SR)
+    hl = RB.stress_headline(st)
+    assert hl["stress_pass"] == 3
+    assert hl["stress_fail"] == 0
+    assert hl["stress_max_hub_rss_mb"] == 60.0
+    assert hl["stress_max_marte_rss_mb"] == 14.0
+    assert hl["stress_max_zoom_p95_ms"] == 35.0
+
+
+def test_stress_plots_one_png_per_axis(tmp_path):
+    st = RB.build_stress(_SR)
+    made = RB.stress_plots(st["by_axis"], str(tmp_path))
+    names = {os.path.basename(p) for p in made}
+    assert "stress_ds_signal_elements.png" in names
+    assert "stress_hub_zoom_reqrate_hz.png" in names
+    for p in made:
+        assert os.path.exists(p)
+
+
+def test_regression_includes_stress_when_present():
+    curr = {"e2e_pass": 5, "stress_max_hub_rss_mb": 60.0}
+    prev = {"e2e_pass": 5, "stress_max_hub_rss_mb": 50.0}
+    labels = dict(RB._LABELS); labels["stress_max_hub_rss_mb"] = "Stress max hub RSS (MB)"
+    directions = dict(RB._DIRECTION); directions["stress_max_hub_rss_mb"] = False
+    rows = RB.regression(curr, prev, labels, directions)
+    row = next(r for r in rows if r["key"] == "stress_max_hub_rss_mb")
+    assert row["delta"] == 10.0
+    assert row["better"] is False  # RSS went up → worse