feat(p17b): a context set that spans TWO bases, and a judge told which one [skip-docs]

``contexts/dekke-og-kontrakt-lindaas-2027`` is the first set whose approaches
route at more than one knowledge base: a1/a2 at n200-2024 (material requirements)
and a3/a4 at r761-2025 (the rig, and the falsification arm). That is the whole
reason it exists -- P17b measures that ONE commission can be run across several.

``bundle.txt`` grows a block per base; a set naming one base is one block, so the
four pre-P17b files parse byte-identically. The reader now has ONE home
(``stress.read_bundle_declarations``): it used to be a private copy in the P14
gate and a second, looser one inside ``stress.main``, and the multi-base form is
exactly the change that would have let them drift.

Rule U becomes the UNION of every declared base, and that is not a formality.
MEASURED 15.09: ``enhetspris`` is absent from n200-2024 and carried by 70 of
r761-2025's 2 756 concepts, so anchors admitted per base would have admitted a
question the pass as a whole CAN ground. It was dropped from the fifth set's
anchors for that reason.

``score_context_set(bundle_id=...)`` restricts the judgement to the approaches
routed at THIS base. Without it, judging the n200 outbox reports the r761
approach as ``not_evaluated``/``absent`` -- a false finding, because that
approach WAS evaluated, against the other base, under the other run_id. That
defect is pinned by its own arm. The judge's CLI refuses to guess when a set
declares several bases, with an rc-0 control on ``--bundle``.

Arm (d) gained a second half: every DECLARED base must be named by some
approach, because a base no approach names is never run.

The P19/B2 fasit denominator moved 26 -> 32 and is asserted, not dropped: six new
references, two of them bare ``prosessnr`` (12.11, 12.12), so B1's
punctuation-and-digits form is now exercised by a fasit and not only by a
known-positive.

Suite 1774/5, golden byte-unchanged.

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

tests/test_stress_judge_loadbearing.py

@@ -486,3 +486,146 @@ def test_k_the_cli_writes_the_verdict_file_and_prints_it(tmp_path: Path) -> None
     payload = json.loads(written.read_text(encoding="utf-8"))
     assert payload["ferdig"] is True
     assert json.loads(proc.stdout)["ferdig"] is True
+
+
+# --------------------------------------------------------------------------------------------
+# P17b DEL 2 — a context set spanning SEVERAL bases is judged ONE base at a time, and the judge
+# is told which. Without that restriction the other base's approach is reported
+# ``not_evaluated``/``absent``, which is a FALSE finding: that approach WAS evaluated, against the
+# other base, under the other ``run_id``.
+# --------------------------------------------------------------------------------------------
+
+
+def _two_base_context(root: Path) -> Path:
+    ctx = root / "ctx2"
+    (ctx / "docs").mkdir(parents=True)
+    (ctx / "bundle.txt").write_text(
+        "name: minibase\nbundle_id: minibase\nname: otherbase\nbundle_id: otherbase\n",
+        encoding="utf-8",
+    )
+    (ctx / "mandate.json").write_text(
+        json.dumps(
+            {
+                "objective": "o",
+                "success_criteria": "s",
+                "approaches": [
+                    {
+                        "id": "a1",
+                        "label": "Here",
+                        "affected_codes": ["CODE-1"],
+                        "claimed_saving_nok": 1000.0,
+                        "bundle_id": "minibase",
+                    },
+                    {
+                        "id": "a2",
+                        "label": "Over there",
+                        "affected_codes": ["CODE-2"],
+                        "claimed_saving_nok": 2000.0,
+                        "bundle_id": "otherbase",
+                    },
+                ],
+            },
+            indent=2,
+        ),
+        encoding="utf-8",
+    )
+    (ctx / "fasit.json").write_text(
+        json.dumps(
+            {
+                "project_id": "proj",
+                "must_cite": [
+                    {
+                        "approach_id": "a1",
+                        "rationale": "why",
+                        "concepts": [{"path": _GOOD, "title": _TITLE, "ref": _REF}],
+                    },
+                    {
+                        "approach_id": "a2",
+                        "rationale": "why",
+                        "concepts": [{"path": _OTHER, "title": "Other", "ref": "Krav 9.9.9-9"}],
+                    },
+                ],
+                "must_refuse": [],
+                "honesty": "synthetic",
+            },
+            indent=2,
+        ),
+        encoding="utf-8",
+    )
+    return ctx
+
+
+def test_a_multi_base_set_is_judged_one_base_at_a_time(tmp_path: Path) -> None:
+    """Told which base this outbox is for, the judge answers for THAT base's approaches only."""
+    base = _minibase(tmp_path)
+    ctx = _two_base_context(tmp_path)
+    outbox = tmp_path / "out"
+    _write_outbox(outbox, "r1-minibase", approach_id="a1", tool_calls=_opened(_GOOD))
+
+    verdict = stress.score_context_set(ctx, outbox, "r1-minibase", base, bundle_id="minibase")
+
+    assert [row.approach_id for row in verdict.approaches] == ["a1"]
+    assert verdict.bundle_id == "minibase"
+    assert verdict.approaches[0].status == "validated"
+
+
+def test_without_the_restriction_the_other_bases_approach_is_falsely_reported_absent(
+    tmp_path: Path,
+) -> None:
+    """The defect the restriction removes, stated as a measurement rather than a worry.
+
+    This is the UNRESTRICTED call on the same outbox: ``a2`` has no artefact here — it was run
+    against the other base, under the other ``run_id`` — and the judge reports it as an approach
+    nobody evaluated, which is exactly the silence ``not_evaluated`` exists to remove.
+    """
+    base = _minibase(tmp_path)
+    ctx = _two_base_context(tmp_path)
+    outbox = tmp_path / "out"
+    _write_outbox(outbox, "r1-minibase", approach_id="a1", tool_calls=_opened(_GOOD))
+
+    verdict = stress.score_context_set(ctx, outbox, "r1-minibase", base)
+
+    rows = {row.approach_id: row for row in verdict.approaches}
+    assert set(rows) == {"a1", "a2"}
+    assert rows["a2"].status == "not_evaluated"
+    assert rows["a2"].not_evaluated_reason == "absent"
+
+
+def test_a_base_no_approach_is_routed_at_has_no_denominator(tmp_path: Path) -> None:
+    base = _minibase(tmp_path)
+    ctx = _two_base_context(tmp_path)
+    outbox = tmp_path / "out"
+    _write_outbox(outbox, "r1-minibase", approach_id="a1")
+
+    with pytest.raises(stress.EmptyMeasurement, match="routed at"):
+        stress.score_context_set(ctx, outbox, "r1-minibase", base, bundle_id="thirdbase")
+
+
+def test_the_cli_refuses_to_guess_which_base_a_multi_base_outbox_is_for(
+    tmp_path: Path, capsys: pytest.CaptureFixture[str]
+) -> None:
+    """Refused, never guessed: picking would score one base's run against another's fasit rows.
+
+    Paired with the rc-0 control below, so "rc 1" cannot be coming from the rest of the argv.
+    """
+    _minibase(tmp_path)
+    ctx = _two_base_context(tmp_path)
+    outbox = tmp_path / "out"
+    _write_outbox(outbox, "r1-minibase", approach_id="a1", tool_calls=_opened(_GOOD))
+
+    argv = [
+        str(ctx),
+        "--outbox-dir",
+        str(outbox),
+        "--run-id",
+        "r1-minibase",
+        "--bundle-root",
+        str(tmp_path),
+    ]
+    assert stress.main(argv) == 1
+    assert "--bundle" in capsys.readouterr().err
+
+    assert stress.main([*argv, "--bundle", "minibase"]) == 0, "control: naming the base works"
+
+    assert stress.main([*argv, "--bundle", "nowhere"]) == 1
+    assert "nowhere" in capsys.readouterr().err