test: neutral names for the reference path and the office-IT baseline

Rename the reference-project helpers and test names (_reference_k,
test_reference_path_*) and the cost-baseline helper (_kontor_it_baseline,
which already returned KONTOR-IT-E1). Names only; no assertion changes.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

tests/test_baseline_visibility_loadbearing.py

@@ -137,7 +137,7 @@ async def test_provenance_records_an_anchored_bundle_run(fresh_store) -> None:
     assert result.provenance.cost_baseline_anchored is True
 
 
-async def test_road_path_is_anchored_by_construction(docs_dir, fresh_store) -> None:
+async def test_reference_path_is_anchored_by_construction(docs_dir, fresh_store) -> None:
     """The reference path derives its baseline from the reference project's own ``cost_items``, so it is
     ALWAYS anchored — the stamp says so rather than leaving the reader to know it."""
     result = await run_project(

tests/test_bundle_id_slack_loadbearing.py

@@ -219,7 +219,7 @@ async def test_the_run_stamps_which_source_answered_and_completes(
     )
 
 
-async def test_the_road_path_stamps_no_bundle_identity_at_all(
+async def test_the_reference_path_stamps_no_bundle_identity_at_all(
     docs_dir: Any, fresh_store: Any
 ) -> None:
     """(e, control) A run with no knowledge base has no bundle identity, and says so by ABSENCE

tests/test_docs_dir_optional_loadbearing.py

@@ -75,7 +75,7 @@ def test_neither_flag_is_still_refused_by_name(capsys: pytest.CaptureFixture[str
     assert "run refused" in err and "--docs-dir" in err and "--bundle-dir" in err
 
 
-def test_the_road_path_still_requires_a_real_docs_dir(
+def test_the_reference_path_still_requires_a_real_docs_dir(
     tmp_path: Path, capsys: pytest.CaptureFixture[str]
 ) -> None:
     """(d) The anti-omvei arm. With no bundle, ``--docs-dir`` is still the only door AND it is

tests/test_navigation_visibility_loadbearing.py

@@ -249,7 +249,7 @@ async def test_run_result_carries_the_trace(tmp_path, fresh_store) -> None:
     assert [s.target for s in result.skipped_links] == [_DANGLING]
 
 
-async def test_road_path_has_an_empty_trace(docs_dir, fresh_store) -> None:
+async def test_reference_path_has_an_empty_trace(docs_dir, fresh_store) -> None:
     """The reference path navigates no bundle, so "nothing was skipped" is literally true there — which
     is exactly why the empty tuple is an honest DEFAULT rather than a withheld fact."""
     result = await run_project(

tests/test_portfolio_concurrent_loadbearing.py

@@ -40,7 +40,7 @@ from test_portfolio import REPLIES
 from test_portfolio_learning_loadbearing import (
     _ALIGNED_REPLY,
     _bundle_kplus1,
-    _road_k,
+    _reference_k,
 )
 
 from portfolio_optimiser import ledger as ledger_mod
@@ -797,7 +797,7 @@ async def test_intra_wave_visibility_is_the_documented_semantic_difference(
     # rebuilt fixture would present as "the sentinel stopped arriving", i.e. as the very semantic
     # difference this test claims to measure. The ``failures`` assertions below exist so that
     # confusion can never happen silently again.
-    pair = (_road_k(tmp_path, rationale=sentinel), _bundle_kplus1(tmp_path))
+    pair = (_reference_k(tmp_path, rationale=sentinel), _bundle_kplus1(tmp_path))
     monkeypatch.setattr("portfolio_optimiser.run.load_reference_projects", lambda: pair)
 
     # k=1 — two waves. The control: the cross-project fold fires and the sentinel arrives.

tests/test_portfolio_learning_loadbearing.py

@@ -57,7 +57,7 @@ def _make_docs(tmp_path, name: str) -> str:
     return str(d)
 
 
-def _road_k(tmp_path, *, rationale: str) -> Project:
+def _reference_k(tmp_path, *, rationale: str) -> Project:
     return Project(
         id="REF-K",
         name="Reference k",
@@ -92,7 +92,7 @@ async def test_verdict_on_k_reaches_kplus1_hypothesis_prompt(
     *k+1*'s hypothesis-generation prompt (both the sentinel rationale and *k*'s verdict id, via the
     ExpeL few-shot). Detach ``bundle_dir=project.bundle_dir`` at run.py:496 → *k+1* runs the reference
     path → the Step-1 fold is skipped → the sentinel never arrives → RED."""
-    k = _road_k(tmp_path, rationale=_SENTINEL)
+    k = _reference_k(tmp_path, rationale=_SENTINEL)
     kplus1 = _bundle_kplus1(tmp_path)
     monkeypatch.setattr("portfolio_optimiser.run.load_reference_projects", lambda: (k, kplus1))
     factory, recorded = make_recording_client_factory(_ALIGNED_REPLY)
@@ -120,7 +120,7 @@ async def test_kplus1_alone_against_fresh_store_carries_no_signal(
     """T-2.0b CAUSALITY CONTROL: running ONLY *k+1* against a fresh (empty) store carries the
     sentinel into NO prompt — proving the signal in T-2.0a is caused by the threaded store, not
     incidental to the fixture (makes the positive test genuinely load-bearing)."""
-    k = _road_k(tmp_path, rationale=_SENTINEL)
+    k = _reference_k(tmp_path, rationale=_SENTINEL)
     kplus1 = _bundle_kplus1(tmp_path)
     monkeypatch.setattr("portfolio_optimiser.run.load_reference_projects", lambda: (k, kplus1))
     factory, recorded = make_recording_client_factory(_ALIGNED_REPLY)
@@ -158,7 +158,7 @@ async def test_dropped_verdict_in_kplus1_inbox_reaches_store(
     )
     write_verdict(str(inbox), dropped)
 
-    k = _road_k(tmp_path, rationale=_SENTINEL)
+    k = _reference_k(tmp_path, rationale=_SENTINEL)
     kplus1 = _bundle_kplus1(tmp_path, verdict_dir=str(inbox))
     monkeypatch.setattr("portfolio_optimiser.run.load_reference_projects", lambda: (k, kplus1))
     factory, _recorded = make_recording_client_factory(_ALIGNED_REPLY)

tests/test_s40_cost_baseline_loadbearing.py

@@ -59,7 +59,7 @@ _FAKE_UNIT_COST = 10_000_000.0
 _FAKE_CLAIM = 3_000_000.0
 
 
-def _fv42_baseline() -> CostBaseline:
+def _kontor_it_baseline() -> CostBaseline:
     return baseline_from_project(
         next(p for p in load_reference_projects() if p.id == "KONTOR-IT-E1")
     )
@@ -83,7 +83,7 @@ def test_fabricated_cost_code_is_rejected() -> None:
     rejected, even though its own arithmetic clears the LP/P90/nominal stages. Detach the
     reconciliation stage and the SAME proposal validates."""
     result = validate_proposal(
-        _proposal(_FAKE_CODE, 1.0, _FAKE_UNIT_COST, _FAKE_CLAIM), baseline=_fv42_baseline()
+        _proposal(_FAKE_CODE, 1.0, _FAKE_UNIT_COST, _FAKE_CLAIM), baseline=_kontor_it_baseline()
     )
     assert isinstance(result, Rejection), "a hallucinated cost code must never reach validated"
     assert "unknown cost code" in result.reason
@@ -95,7 +95,8 @@ def test_real_baseline_line_still_validates() -> None:
     rejection above is caused by the code being absent from the baseline, not by the new stage
     rejecting everything."""
     result = validate_proposal(
-        _proposal(_REAL_CODE, _REAL_QTY, _REAL_UNIT_COST, _REAL_CLAIM), baseline=_fv42_baseline()
+        _proposal(_REAL_CODE, _REAL_QTY, _REAL_UNIT_COST, _REAL_CLAIM),
+        baseline=_kontor_it_baseline(),
     )
     assert isinstance(result, ValidatedProposal)
 
@@ -117,7 +118,7 @@ def test_inflated_unit_cost_on_a_real_code_is_rejected() -> None:
     line then validates, because the code itself is genuine."""
     inflated = _REAL_UNIT_COST * 1.20
     result = validate_proposal(
-        _proposal(_REAL_CODE, _REAL_QTY, inflated, _REAL_CLAIM), baseline=_fv42_baseline()
+        _proposal(_REAL_CODE, _REAL_QTY, inflated, _REAL_CLAIM), baseline=_kontor_it_baseline()
     )
     assert isinstance(result, Rejection)
     assert "unit_cost" in result.reason and _REAL_CODE in result.reason
@@ -127,7 +128,7 @@ def test_inflated_quantity_on_a_real_code_is_rejected() -> None:
     """RED: the same for quantity — a real code at an invented quantity (+20%) is rejected."""
     result = validate_proposal(
         _proposal(_REAL_CODE, _REAL_QTY * 1.20, _REAL_UNIT_COST, _REAL_CLAIM),
-        baseline=_fv42_baseline(),
+        baseline=_kontor_it_baseline(),
     )
     assert isinstance(result, Rejection)
     assert "quantity" in result.reason
@@ -139,7 +140,7 @@ def test_within_tolerance_deviation_is_admitted() -> None:
     at all."""
     result = validate_proposal(
         _proposal(_REAL_CODE, _REAL_QTY, _REAL_UNIT_COST * 1.02, _REAL_CLAIM),
-        baseline=_fv42_baseline(),
+        baseline=_kontor_it_baseline(),
     )
     assert isinstance(result, ValidatedProposal)
 
@@ -149,7 +150,7 @@ def test_tolerance_is_configurable() -> None:
     caller-supplied tolerance."""
     result = validate_proposal(
         _proposal(_REAL_CODE, _REAL_QTY, _REAL_UNIT_COST * 1.02, _REAL_CLAIM),
-        baseline=_fv42_baseline(),
+        baseline=_kontor_it_baseline(),
         tolerance=0.001,
     )
     assert isinstance(result, Rejection)
@@ -204,7 +205,9 @@ def _factory(reply: str):
     return factory
 
 
-async def test_road_path_anchors_the_gate_to_the_reference_baseline(docs_dir, fresh_store) -> None:
+async def test_reference_path_anchors_the_gate_to_the_reference_baseline(
+    docs_dir, fresh_store
+) -> None:
     """RED (reference wiring): a numerically-impeccable fabricated cost line is REJECTED end-to-end
     through ``run_project``. Detach the reference-path baseline (stop passing it) and the same run
     returns a ValidatedProposal."""
@@ -220,7 +223,7 @@ async def test_road_path_anchors_the_gate_to_the_reference_baseline(docs_dir, fr
     assert "unknown cost code" in result.outcome.reason
 
 
-async def test_road_path_control_real_line_validates(docs_dir, fresh_store) -> None:
+async def test_reference_path_control_real_line_validates(docs_dir, fresh_store) -> None:
     """Causality control for the reference wiring: the real 05.2 line validates through the same path."""
     result = await run_project(
         "KONTOR-IT-E1",

tests/test_ungiven_verdict_loadbearing.py

@@ -241,7 +241,7 @@ def _make_docs(tmp_path: Path, name: str) -> str:
     return str(d)
 
 
-def _road_k(tmp_path: Path, *, verdict_input: dict[str, str] | None) -> Project:
+def _reference_k(tmp_path: Path, *, verdict_input: dict[str, str] | None) -> Project:
     return Project(
         id="REF-K",
         name="Reference k",
@@ -275,7 +275,7 @@ async def test_a_given_verdict_on_k_does_reach_kplus1(
     """T4 CONTROL (mirrors ``test_portfolio_learning_loadbearing``): when an expert DID review
     project *k*, that verdict reaches *k+1*'s hypothesis prompt. This is the event T5 denies —
     proving first that it can happen is what makes T5's negative assert mean anything."""
-    k = _road_k(tmp_path, verdict_input={"decision": "approved", "rationale": _SENTINEL})
+    k = _reference_k(tmp_path, verdict_input={"decision": "approved", "rationale": _SENTINEL})
     kplus1 = _bundle_kplus1(tmp_path)
     monkeypatch.setattr("portfolio_optimiser.run.load_reference_projects", lambda: (k, kplus1))
     factory, recorded = make_recording_client_factory(_ALIGNED_REPLY)
@@ -295,7 +295,7 @@ async def test_an_ungiven_verdict_on_k_never_reaches_kplus1(
     prompt — no verdict is minted, none enters the shared store, and *k*'s candidate key never
     shows up as a prior judgement. RED before the seam: *k* minted an ``approved`` verdict from a
     ``verdict_input`` no expert supplied, and the threaded store carried it forward."""
-    k = _road_k(tmp_path, verdict_input=None)
+    k = _reference_k(tmp_path, verdict_input=None)
     kplus1 = _bundle_kplus1(tmp_path)
     monkeypatch.setattr("portfolio_optimiser.run.load_reference_projects", lambda: (k, kplus1))
     factory, recorded = make_recording_client_factory(_ALIGNED_REPLY)