docs: multi-base som invariant + den ende-til-ende-sloeyfa som beviser den (ORDRE 20260825T080753Z)

CLAUDE.md-invarianten «Multi-base er en PARTISJON, aldri en videre
run_project-signatur» baerer hele designet: den strukturelle grunnen til at
run_project ikke KAN ta flere bundle_dir (fire enkeltverdier avledet fra DEN
basen), de tre soemmene, hvorfor dispatchen ikke tar project_id, de tolv maalte
mutasjonene, og de fire uttalte aerlighets-grensene - inkludert at CLI-en er
BEVISST uroert (§ C.8 ber om ETT nytt kallsted i run.py, levert i 57; et
repeterbart --bundle-dir er en NY operatoerflate og en egen beslutning).

README faar multi-base-doeren beskrevet der --explore alt er beskrevet, med den
samme nekten uttalt for en leser som ikke leser CLAUDE.md: en hypotese som ikke
navngir noen base blir NEKTET naar flere er konfigurert, aldri rutet til en
gjetning.

T22 er ende-til-ende-vitnet, og det eneste stedet de tre soemmene moetes:
prompt + TO baser -> hypotesiseren former to retninger og navngir hver sin base
-> route_by_bundle partisjonerer -> hver base sin run_project svarer for SIN
hypotese og ingen andres. Assertet paa COVERAGE-radene, ikke paa kall-argumenter,
fordi det er rapporten en fagperson faktisk leser: en approach som havnet i feil
base ville fortsatt sett evaluert ut.

1021 passed / 5 skipped; golden demo-transcript.stdout byte-uendret
(ea8c534773acdbe41ae68f2c55724d69aaf8be4f); mypy/ruff rene.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01L3YHobQC3WzYVoxSgZus4d

tests/test_multibase_loadbearing.py

@@ -667,3 +667,67 @@ async def test_one_store_is_threaded_across_every_base(
 
     assert len(calls) == 2
     assert all(c["store"] is store for c in calls)
+
+
+@pytest.mark.asyncio
+async def test_exploration_and_dispatch_close_the_loop_over_two_bases(tmp_path: Path) -> None:
+    """T22: the end-to-end witness for § C.7 — prompt + TWO bases -> mandate -> two pipelines.
+
+    Every test above pins one seam. This one is the only place the three meet: the hypothesiser
+    shapes two directions and names a DIFFERENT base for each, ``route_by_bundle`` partitions them,
+    and each base's own ``run_project`` answers for its own hypothesis and for nobody else's. Every
+    reply is scripted, so what is shown is that the plumbing closes — never that a live model would
+    shape either direction well (the demo's §1 honesty limit, unchanged).
+
+    Assertion is on the COVERAGE rows rather than on call arguments, because that is the report an
+    expert actually reads: an approach that reached the wrong base would still appear evaluated.
+    """
+    bases = []
+    for src in (_BYGG, _TUNNEL):
+        dst = tmp_path / src.name
+        shutil.copytree(src, dst)
+        bases.append(str(dst))
+
+    exploration = await explore.explore(
+        _PROMPT,
+        contract=_CONTRACT,
+        bundle_dirs=tuple(bases),
+        client_factory=_factory(
+            ledgers=[
+                _ledger_json(satisfied=False, speaker=explore.HYPOTHESISER_ROLE),
+                _ledger_json(satisfied=True, speaker=explore.HYPOTHESISER_ROLE),
+            ],
+            hypothesiser=[
+                _hypothesis_line("Behovsstyrt lys", "fixtures are 1990s", "bygg-energi-mikro")
+                + "\n"
+                + _hypothesis_line("Nattsenking", "the tunnel runs lit all night", "tunnel-hauglia")
+            ],
+        ),
+    )
+
+    assert [a.bundle_id for a in exploration.mandate.approaches] == [
+        "bygg-energi-mikro",
+        "tunnel-hauglia",
+    ]
+
+    def factory(role: str) -> BaseChatClient:
+        return ScriptedChatClient(
+            reply_selector=lambda _blob, _role: _reply_for("ENERGI-TOTAL-EL", 300000, 1.0, 30_000),
+            role=role,
+        )
+
+    result = await run_mandate_across_bundles(
+        exploration.mandate,
+        tuple(bases),
+        "local",
+        verdict_input=_VERDICT_INPUT,
+        store=VerdictStore(verdicts=[]),
+        client_factory=factory,
+        max_rounds=1,
+    )
+
+    assert [r.bundle_id for r in result.runs] == ["bygg-energi-mikro", "tunnel-hauglia"]
+    assert [{row.id for row in r.result.coverage} for r in result.runs] == [
+        {"hypothesis-1", "own-proposal"},
+        {"hypothesis-2", "own-proposal"},
+    ]