fix(major2): --proposal-review komponerer med --resume, og armen som beviser det

To funn, ETT commit, fordi de deler vitnet ved konstruksjon: 02159d21
(run.py:2738, PLAN_EXECUTE_DRIFT) er vakten, da485928
(tests/...:1344, MISSING_TEST) er armen som skulle sett den. AA dele dem ville
krevd en kastbar duplikattest.

VAKTEN: `if args.checkpoint_dir is not None` nektet --proposal-review for HVER
argv med en checkpoint-katalog - men --resume KREVER --checkpoint-dir
(run.py:2776), saa komposisjonen nekten selv anbefaler («pass --proposal-review
at --resume instead») var unaabar, og run.py:2218-helpen, README.md:546 og
MAJOR-2-raden beskrev en sti ingen argv kunne ta. Vakten nekter naa en PARK
(en etappe som returnerer foer noen kandidat finnes), aldri et LOEFT.

ARMEN: `test_the_door_composes_with_resume` sendte hverken --resume,
--checkpoint-dir eller --review-inbox - den var en vanlig enkeltkjoering T13
allerede dekket, altsaa groenn mot nettopp den defekten den var navngitt for.
Den driver naa en EKTE resume: dag 1 parkerer en ekte plan-review gjennom
run.main, ekspertens svar legges i en ekte innboks, og dag N sender
--resume ... --checkpoint-dir ... --review-inbox ... --proposal-review med
run_project innspilt og _refuse_model som kontroll paa null modellkall.

MAALT, i denne rekkefoelgen (Iron Law): armen skrevet FOERST og kjoert mot
uendret vakt -> ROED med nettopp nektlinja i stderr («pass --proposal-review at
--resume instead»), calls == []. Etter vakt-fiksen: 49 passed i fila, og
park-nekten (test_the_door_and_a_parked_exploration_contradict, M39) staar
groenn - den sender --explore uten --resume.

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

src/portfolio_optimiser/run.py

@@ -2735,7 +2735,12 @@ def main(argv: list[str] | None = None) -> int:
                 file=sys.stderr,
             )
             return 1
-        if args.checkpoint_dir is not None:
+        # ``and args.resume is None`` is load-bearing, not defensive: --resume REQUIRES
+        # --checkpoint-dir (:2776 below), so a bare --checkpoint-dir test refused the very
+        # composition this message recommends, and the help text, README and the invariant row all
+        # described a path no argv could take. What is being refused is a PARK (a leg that returns
+        # before any candidate exists), never a LIFT (a leg that runs the pipeline to a candidate).
+        if args.checkpoint_dir is not None and args.resume is None:
             print(
                 "run refused: --proposal-review and --checkpoint-dir: a parked exploration "
                 "returns before any candidate exists, so the review would never be asked — pass "

tests/test_proposal_review_loop_loadbearing.py

@@ -1325,14 +1325,124 @@ def test_the_door_and_a_parked_exploration_contradict(
     assert "--resume" in err
 
 
-def test_the_door_composes_with_resume(tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
+#: Day 1's parked exploration, driven exactly as an operator drives it: a real ``--explore`` leg
-    """A3, VERIFIED rather than deferred: the resume block yields the parked exploration's mandate
+#: with ``enable_plan_review`` armed and NO reviewer at the terminal, so the loop parks. The
-    and falls through to the SAME full-run dispatch, so the reviewer built at the CLI is reached.
+#: proposal-review door is deliberately absent here — that argv is the refusal this arm's sibling
-    Detach point: refusing ``--resume`` together with the door, or forgetting to pass the reviewer
+#: (``…and_a_parked_exploration_contradict``) keeps green.
-    on that path.
+_RESUME_RUN_ID = "proposal-review-resume"
+
+_RESUME_MANAGER_REPLY = json.dumps(
+    {
+        "is_request_satisfied": {"reason": "r", "answer": True},
+        "is_in_loop": {"reason": "r", "answer": False},
+        "is_progress_being_made": {"reason": "r", "answer": True},
+        "next_speaker": {"reason": "r", "answer": "hypothesiser"},
+        "instruction_or_question": {"reason": "r", "answer": "go"},
+    }
+)
+
+
+def _resume_replies_file(tmp_path: Path) -> str:
+    """Both time-scales' roles in one file: the exploration's three and the debate's two. A
+    missing ``navigator`` key is the ``KeyError`` M40 of økt 64 — the resume leg builds an
+    exploration too, so it needs the same roster the park leg did."""
+    path = tmp_path / "resume-replies.json"
+    path.write_text(
+        json.dumps(
+            {
+                "proposer": _run_reply(_CLI_MEASURE, 30_000),
+                "checker": "VERDICT: APPROVE",
+                "manager": _RESUME_MANAGER_REPLY,
+                "navigator": "NAVIGATOR: read the index.",
+                "hypothesiser": "HYPOTHESIS: "
+                + json.dumps({"label": "Night setback", "rationale": "y"}),
+            }
+        ),
+        encoding="utf-8",
+    )
+    return str(path)
+
+
+def _resume_config_file(tmp_path: Path) -> str:
+    path = tmp_path / "resume-exploration.json"
+    path.write_text(
+        json.dumps(
+            {
+                "max_rounds": 4,
+                "max_tokens": 200_000,
+                "max_stall_count": 2,
+                "max_reset_count": 1,
+                "max_plan_revisions": 2,
+                "enable_plan_review": True,
+            }
+        ),
+        encoding="utf-8",
+    )
+    return str(path)
+
+
+def _park_then_answer(tmp_path: Path) -> None:
+    """Day 1 and the days between: park a real plan review, then drop the expert's answer in the
+    inbox. Both halves go through the shipped surfaces — a hand-written question file would test
+    the fixture, not the door."""
+    outbox = tmp_path / "outbox"
+    assert (
+        run.main(
+            [
+                _RUN_PID,
+                "--docs-dir",
+                str(_BUNDLE_DIR),
+                "--bundle-dir",
+                str(_BUNDLE_DIR),
+                "--explore",
+                "Find the cheapest saving.",
+                "--explore-config",
+                _resume_config_file(tmp_path),
+                "--scripted-replies",
+                _resume_replies_file(tmp_path),
+                "--outbox-dir",
+                str(outbox),
+                "--checkpoint-dir",
+                str(tmp_path / "checkpoints"),
+                "--run-id",
+                _RESUME_RUN_ID,
+            ]
+        )
+        == 0
+    )
+    question = json.loads(
+        (outbox / f"{_RESUME_RUN_ID}-plan-review.json").read_text(encoding="utf-8")
+    )
+    inbox = tmp_path / "review-inbox"
+    inbox.mkdir(parents=True, exist_ok=True)
+    (inbox / f"{_RESUME_RUN_ID}-plan-review-answer.json").write_text(
+        json.dumps(
+            {
+                "run_id": _RESUME_RUN_ID,
+                "request_id": question["request_id"],
+                "decision": "approve",
+            }
+        ),
+        encoding="utf-8",
+    )
+
+
+def test_the_door_composes_with_resume(tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
+    """A3, and the WITNESS the review found missing: the ``--checkpoint-dir`` refusal points the
+    operator at ``--resume``, and ``--resume`` itself REQUIRES ``--checkpoint-dir`` — so before
+    this arm the recommended composition was refused by the very message that recommended it, and
+    nothing in the suite could see it. Detach point: reverting the guard to a bare
+    ``if args.checkpoint_dir is not None``.
+
+    The argv is a REAL resume: day 1 parks a real plan review through ``run.main``, the expert's
+    answer is dropped in a real inbox, and day N passes ``--resume … --checkpoint-dir …
+    --review-inbox … --proposal-review``. The arm it replaced sent none of those three flags and
+    was a plain single-project run T13 already covered — green against the defect it was named
+    for. ``run_project`` is a recorder, so what is measured is the WIRING at the fall-through, and
+    ``_refuse_model`` proves the recorded call is the ONLY place a model would have been reached
+    from."""
+    _park_then_answer(tmp_path)
 
-    ``run_project`` is replaced by a recorder, so the arm measures the WIRING rather than a whole
-    resumed exploration."""
     calls: list[dict[str, Any]] = []
 
     async def _recorder(*args: Any, **kwargs: Any) -> Any:
@@ -1349,15 +1459,19 @@ def test_the_door_composes_with_resume(tmp_path: Path, monkeypatch: pytest.Monke
             "--bundle-dir",
             str(_BUNDLE_DIR),
             "--scripted-replies",
-            _cli_replies_file(tmp_path),
+            _resume_replies_file(tmp_path),
             "--outbox-dir",
             str(tmp_path / "outbox"),
-            "--run-id",
+            "--checkpoint-dir",
-            _RUN_ID,
+            str(tmp_path / "checkpoints"),
+            "--review-inbox",
+            str(tmp_path / "review-inbox"),
+            "--resume",
+            _RESUME_RUN_ID,
             "--proposal-review",
         ]
     )
-    assert len(calls) == 1
+    assert len(calls) == 1, "the resume must fall through to the full-run dispatch, not be refused"
     assert calls[0]["proposal_reviewer"] is not None