test(v1-gate): the MAF list is operator-approved; row 5 reads 3 of 8

The eight U-IDs and their type pointers were checked against the approved
list (no deviation) and the data file now says approved, with the date and
the source. Row 5 no longer reports "not approved" but the measured count:
3 of 8 (U12, U4, U6), because a point counts only when every type it points
at is green and only types 1, 3 and 7 are. No gate logic changed.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

src/portfolio_optimiser/evals/v1_gate.json

@@ -46,7 +46,9 @@
     "tests/test_v1_probes.py::test_row6_a_run_level_declaration_does_not_stand_in_for_the_approach"
   ],
   "maf_points": {
-    "approved": false,
+    "approved": true,
+    "approved_on": "2026-09-17",
+    "approved_by": "operatørgodkjent",
     "points": [
       {"u_id": "U13", "construct": "MagenticPlanReviewResponse", "package": "agent_framework",
        "callsite": {"module": "explore.py", "scope": "_drive"}, "types": [1, 2]},

tests/test_v1_gate.py

@@ -234,13 +234,42 @@ def test_row4_a_line_kept_once_counts_once(tmp_path: Path) -> None:
 
 
 def test_row5_is_red_until_the_operator_approves_the_list() -> None:
-    assert _CONFIG["maf_points"]["approved"] is False
+    unapproved = {**_CONFIG["maf_points"], "approved": False}
     verdicts = gate.green_types(_CONFIG["feedback_types"], _all_pass(_ALL_NODEIDS))
-    row = gate.score_maf(_CONFIG["maf_points"], verdicts, gate._PACKAGE_SRC)
+    row = gate.score_maf(unapproved, verdicts, gate._PACKAGE_SRC)
     assert (row.k, row.status, row.reason) == (0, gate.RED, "M ikke godkjent av operatøren")
     assert "presence 7 av 8" in row.diagnostics
 
 
+def test_row5_the_approved_list_counts_only_points_whose_types_are_green() -> None:
+    """The tracked list is operator-approved (17.09): eight U-IDs, and a point counts only when
+    every type it points at is green. With today's green types (1, 3, 7) that is U12, U4, U6."""
+    maf = _CONFIG["maf_points"]
+    assert (maf["approved"], maf["approved_on"], maf["approved_by"]) == (
+        True,
+        "2026-09-17",
+        "operatørgodkjent",
+    )
+    assert [(p["u_id"], p["types"]) for p in maf["points"]] == [
+        ("U13", [1, 2]),
+        ("U9", [1, 8]),
+        ("U12", [1]),
+        ("U4", [3]),
+        ("U7", [4]),
+        ("U11", [5]),
+        ("U5", [6]),
+        ("U6", [7]),
+    ]
+    today = {
+        n: ("passed" if int(t) in (1, 3, 7) else "failed")
+        for t, spec in _CONFIG["feedback_types"].items()
+        for n in spec["evidence"]
+    }
+    row = gate.score_maf(maf, gate.green_types(_CONFIG["feedback_types"], today), gate._PACKAGE_SRC)
+    assert (row.k, row.n, row.status) == (3, 8, gate.RED)
+    assert all(p not in " ".join(row.exceptions) for p in ("U12 ", "U4 ", "U6 "))
+
+
 def _synthetic_src(tmp: Path, *, comment_only: bool = False) -> Path:
     body = (
         "# uses SkillsProvider\n" if comment_only else "def build():\n    return SkillsProvider()\n"
@@ -397,6 +426,6 @@ def test_the_command_is_red_today_with_every_row_in_its_output(tmp_path: Path) -
     assert (rows["rounds"]["k"], rows["changes"]["k"]) == (0, 0)
     assert (rows["types"]["k"], rows["types"]["n"]) == (3, 8)
     assert rows["kept"]["status"] == gate.RED
-    assert rows["maf"]["reason"] == "M ikke godkjent av operatøren"
+    assert (rows["maf"]["k"], rows["maf"]["n"], rows["maf"]["status"]) == (3, 8, gate.RED)
     assert rows["undeclared"]["status"] == gate.RED
     assert rows["named"]["failing"] is False