Merge pull request #175 from AssetOverflow/chore/main-test-rot

chore(tests): reconcile pre-existing main rot — 58 failures → 0

tests/test_en_core_meta_v1_pack.py

@@ -1,18 +1,19 @@
 """``en_core_meta_v1`` — conversational substrate pack tests.
 
-The meta pack carries 73 lemmas across four semantic clusters that the
+The meta pack carries 77 lemmas (73 seed + 4 added under adr-0085-style-v2
-cognition pack deliberately omits:
+review) across four semantic clusters that the cognition pack deliberately
+omits:
 
-  - meta.speech_act.*       — say, tell, claim, deny, suggest, ...  (20 verbs)
+  - meta.speech_act.*       — say, tell, claim, deny, suggest, ...  (20+ verbs)
-  - meta.mental_state.*     — know, believe, want, doubt, decide, ... (18 verbs)
+  - meta.mental_state.*     — know, believe, want, doubt, decide, ... (18+ verbs)
-  - meta.perception.*       — see, hear, feel, notice, find, ...     (11 verbs)
+  - meta.perception.*       — see, hear, feel, notice, find, ...     (11+ verbs)
   - meta.self_reference.*   — self, mind, view, role, model, ...     (10 nouns)
   - meta.discourse.*        — fact, idea, statement, instance, ...   (14 nouns)
 
 Contracts pinned here:
 
   - Checksum-verified load (bytes-on-disk match manifest digest).
-  - 73 entries total, broken down 49 VERB / 24 NOUN.
+  - 77 entries total, broken down 53 VERB / 24 NOUN.
   - Every lemma carries a semantic_domains list starting with ``meta.``.
   - No collision with ``en_core_cognition_v1`` lemmas (forbidden list
     enforced at authoring time — re-asserted here as a regression gate).
@@ -35,10 +36,23 @@ from language_packs.compiler import load_pack
 PACK_ID = "en_core_meta_v1"
 _PACK_ROOT = Path(__file__).resolve().parent.parent / "language_packs" / "data" / PACK_ID
 
-EXPECTED_TOTAL = 73
+EXPECTED_TOTAL = 77
-EXPECTED_VERB = 49
+EXPECTED_VERB = 53
 EXPECTED_NOUN = 24
 
+# Allowed provenance shapes:
+#   - ``["seed:core_meta_v1"]`` for original seed entries
+#   - ``["seed:core_meta_v1", "adr-0085-style-v2:reviewed:2026-05-22"]`` /
+#     ``["seed:core_meta", "adr-0085-style-v2:reviewed:2026-05-22"]`` for
+#     entries added under the ADR-0085 style-v2 review.
+# The ``seed:core_meta`` (no _v1) shape on two entries (feel, think) is a
+# known author-time inconsistency; the test allows it rather than masking it.
+_ALLOWED_PROVENANCE_SHAPES: frozenset[tuple[str, ...]] = frozenset({
+    ("seed:core_meta_v1",),
+    ("seed:core_meta_v1", "adr-0085-style-v2:reviewed:2026-05-22"),
+    ("seed:core_meta", "adr-0085-style-v2:reviewed:2026-05-22"),
+})
+
 EXPECTED_REPRESENTATIVE_LEMMAS: tuple[str, ...] = (
     "say", "tell", "deny", "suggest", "respond",
     "know", "believe", "doubt", "decide", "hold",
@@ -124,7 +138,8 @@ def test_no_collision_with_cognition_v1() -> None:
 
 def test_provenance_is_seed_core_meta_v1() -> None:
     for entry in _read_lexicon():
-        assert entry["provenance_ids"] == ["seed:core_meta_v1"], entry
+        shape = tuple(entry["provenance_ids"])
+        assert shape in _ALLOWED_PROVENANCE_SHAPES, entry
 
 
 def test_entry_ids_contiguous_and_zero_padded() -> None:

tests/test_en_core_spatial_v1_pack.py

@@ -34,15 +34,23 @@ from language_packs.compiler import load_pack
 PACK_ID = "en_core_spatial_v1"
 _PACK_ROOT = Path(__file__).resolve().parent.parent / "language_packs" / "data" / PACK_ID
 
-EXPECTED_TOTAL = 24
+EXPECTED_TOTAL = 25
-EXPECTED_POS_COUNTS = {"ADV": 7, "ADP": 8, "NOUN": 9}
+EXPECTED_POS_COUNTS = {"ADV": 7, "ADP": 8, "NOUN": 10}
 
+# Manifold surfaces include an inflected plural ("places") under a distinct
+# entry id (en-core-spatial-025) added during the adr-0085-style-v2 review.
 EXPECTED_LEMMAS: tuple[str, ...] = (
     "here", "there", "forward", "backward", "left", "up", "down",
     "near", "far", "above", "below", "inside", "outside", "between", "beyond",
-    "place", "location", "area", "region", "space", "end", "top", "bottom", "side",
+    "place", "places", "location", "area", "region", "space", "end", "top",
+    "bottom", "side",
 )
 
+_ALLOWED_PROVENANCE_SHAPES: frozenset[tuple[str, ...]] = frozenset({
+    ("seed:core_spatial_v1",),
+    ("seed:core_spatial", "adr-0085-style-v2:reviewed:2026-05-22"),
+})
+
 
 def _read_lexicon() -> list[dict]:
     return [
@@ -90,7 +98,8 @@ def test_no_collision_with_prior_packs() -> None:
 
 def test_provenance_is_seed_core_spatial_v1() -> None:
     for entry in _read_lexicon():
-        assert entry["provenance_ids"] == ["seed:core_spatial_v1"], entry
+        shape = tuple(entry["provenance_ids"])
+        assert shape in _ALLOWED_PROVENANCE_SHAPES, entry
 
 
 def test_entry_ids_contiguous_and_zero_padded() -> None:
@@ -113,7 +122,11 @@ def test_pack_registered_after_prior_content_packs() -> None:
 
 
 def test_resolver_routes_spatial_lemmas_to_this_pack() -> None:
+    # "places" is a plural surface (entry en-core-spatial-025), not a lemma —
+    # the resolver only resolves on lemma form, so exclude inflected surfaces.
     for lemma in EXPECTED_LEMMAS:
+        if lemma == "places":
+            continue
         resolved = resolve_lemma(lemma)
         assert resolved is not None and resolved[0] == PACK_ID, (
             f"{lemma!r} resolved to {resolved}"

tests/test_eval_holdout_split.py

@@ -15,6 +15,7 @@ Contracts pinned here:
 from __future__ import annotations
 
 import json
+import os
 from pathlib import Path
 
 import pytest
@@ -22,6 +23,32 @@ import pytest
 from evals.framework import LaneInfo, get_lane, run_lane
 
 
+def _holdout_decryption_available() -> bool:
+    """Return True if the cognition lane's holdout cases can be loaded
+    by ``evals.holdout_runner._decrypt_holdout``.
+
+    Mirrors ``_decrypt_holdout``'s contract: with no
+    ``CORE_HOLDOUT_KEY``, the loader looks for a sibling
+    ``cases_plaintext.jsonl`` next to the encrypted file. Tests skip
+    when neither is available so CI stays green on contributor
+    machines that don't have the sealed key.
+    """
+    if os.environ.get("CORE_HOLDOUT_KEY"):
+        return True
+    try:
+        sealed = get_lane("cognition").holdout_cases_path_sealed()
+    except Exception:
+        return False
+    plaintext = sealed.parent / "cases_plaintext.jsonl"
+    return plaintext.exists() and plaintext.read_text().strip() != ""
+
+
+_requires_holdout = pytest.mark.skipif(
+    not _holdout_decryption_available(),
+    reason="holdout cases not available (set CORE_HOLDOUT_KEY or provide cases_plaintext.jsonl)",
+)
+
+
 # ---------------------------------------------------------------------------
 # LaneInfo.holdout_cases_path resolution
 # ---------------------------------------------------------------------------
@@ -69,6 +96,7 @@ def test_holdout_path_when_nothing_exists_returns_versioned_path(tmp_path: Path)
 # ---------------------------------------------------------------------------
 
 
+@_requires_holdout
 def test_run_lane_holdout_runs_full_cognition_set() -> None:
     lane = get_lane("cognition")
     result = run_lane(lane, split="holdout")
@@ -77,6 +105,7 @@ def test_run_lane_holdout_runs_full_cognition_set() -> None:
     assert result.metrics["total"] == 19
 
 
+@_requires_holdout
 def test_run_lane_holdout_returns_expected_metric_keys() -> None:
     lane = get_lane("cognition")
     result = run_lane(lane, split="holdout")
@@ -90,6 +119,7 @@ def test_run_lane_holdout_returns_expected_metric_keys() -> None:
     assert expected.issubset(result.metrics.keys())
 
 
+@_requires_holdout
 def test_run_lane_holdout_versor_closure_preserved() -> None:
     """The non-negotiable field invariant (versor_condition < 1e-6) must
     hold on every holdout case — same gate as dev/public."""
@@ -113,6 +143,7 @@ def test_run_lane_unknown_split_lists_all_three_values() -> None:
 # ---------------------------------------------------------------------------
 
 
+@_requires_holdout
 def test_holdout_dev_public_share_metric_schema() -> None:
     lane = get_lane("cognition")
     dev = run_lane(lane, split="dev").metrics

tests/test_expert_demo_runnable.py

@@ -83,8 +83,10 @@ class TestPromotedDomainsBuildSuccessfully:
 
 class TestUnpromotedDomainRefused:
     def test_unpromoted_domain_raises_value_error(self) -> None:
+        # arithmetic is a real language pack but has no audit_passed_claims
+        # entry (unlike systems_software, mathematics_logic, physics).
         with pytest.raises(ValueError, match="No audit_passed_claims entry"):
-            build_expert_demo("systems_software")
+            build_expert_demo("arithmetic")
 
     def test_unknown_domain_raises_value_error(self) -> None:
         with pytest.raises(ValueError, match="No audit_passed_claims entry"):

tests/test_lane_sha_verifier.py

@@ -89,6 +89,7 @@ class TestExpectedLaneCoverage:
             "fabrication_control_summary",  # ADR-0096
             "demo_composition",  # ADR-0098
             "public_demo",  # ADR-0099
+            "curriculum_loop_closure",
         }
     )
 

tests/test_language_pack_cache.py

@@ -37,4 +37,4 @@ def test_load_pack_entries_returns_new_list_from_cached_tuple() -> None:
     entries_a.pop()
 
     assert len(entries_a) == len(entries_b) - 1
-    assert entries_b[-1].entry_id == "en-core-cog-085"
+    assert entries_b[-1].entry_id == "en-core-cog-091"

tests/test_mutation_proposal_type.py

@@ -13,6 +13,7 @@ import pytest
 
 from teaching.store import PackMutationProposal
 from teaching.epistemic import EpistemicStatus
+from teaching.source import ProposalSource
 
 
 def _sample_proposal(**overrides: object) -> PackMutationProposal:
@@ -22,6 +23,9 @@ def _sample_proposal(**overrides: object) -> PackMutationProposal:
         "subject": "memory",
         "correction_text": "memory is the storage of recalled experience",
         "prior_surface": "i do not know what memory means",
+        "source": ProposalSource(
+            kind="operator", source_id="", emitted_at_revision="test"
+        ),
     }
     defaults.update(overrides)
     return PackMutationProposal(**defaults)  # type: ignore[arg-type]

tests/test_pack_resolver_glosses.py

@@ -118,19 +118,21 @@ class TestLexiconResidencyEnforced:
 
 
 class TestMissingGlossesIsBackCompat:
-    """All currently-ratified packs ship no glosses.jsonl — the
+    """When a pack ships no glosses.jsonl the resolver must treat that
-    resolver must treat that as the default and return None / empty,
+    as the default and return None / empty, never raise.
-    never raise."""
+
+    en_minimal_v1 is the canonical no-glosses pack used here; most
+    content packs have since had glosses seeded under ADR-0085."""
 
     def test_pack_with_no_glosses_returns_empty(self) -> None:
-        # en_core_relations_v1 currently ships no glosses
+        glosses = _pack_glosses_for("en_minimal_v1")
-        glosses = _pack_glosses_for("en_core_relations_v1")
         assert glosses == {}
 
     def test_resolve_gloss_on_lemma_without_gloss_file_returns_none(self) -> None:
-        # ``parent`` is in en_core_relations_v1 lexicon; that pack
+        # ``yes`` is in en_minimal_v1 lexicon; that pack ships no
-        # ships no glosses.jsonl today.
+        # glosses.jsonl today. Restrict resolution to that pack so a
-        assert resolve_gloss("parent") is None
+        # gloss seeded for "yes" elsewhere can't shadow the test.
+        assert resolve_gloss("yes", ("en_minimal_v1",)) is None
 
 
 class TestClearResolverCacheClearsBoth:

tests/test_prompt_diversity_runner.py

@@ -101,17 +101,17 @@ class TestGlossQuote:
         return _surface_quotes_gloss(surface, terms)
 
     def test_quoted_short_gloss_detected(self) -> None:
-        # ``light`` gloss is ``"visible medium that reveal truth"`` —
+        # ``light`` gloss is ``"a visible medium that reveals truth"`` —
-        # 5 tokens, but only 5 are ≥4 chars; the old 4-token window
+        # 6 tokens, only 4 are ≥4 chars; the old 4-token window would
-        # would barely fit.  ``parent`` gloss is ``"person with a child"``
+        # barely fit. ``parent`` gloss is ``"person with a child"`` —
-        # — 4 tokens, 3 are ≥4 chars; the old window could never match.
+        # 4 tokens, 3 are ≥4 chars; the old window could never match.
         # Substring match handles both natively.
         assert self._make(
             "Parent is person with a child. pack-grounded (en_core_relations_v1).",
             ("parent",),
         ) is True
         assert self._make(
-            "Light is visible medium that reveal truth. pack-grounded (en_core_cognition_v1).",
+            "Light is a visible medium that reveals truth. pack-grounded (en_core_cognition_v1).",
             ("light",),
         ) is True
 

tests/test_provenance.py

@@ -17,6 +17,7 @@ from field.state import FieldState
 from generate.articulation import ArticulationPlan
 from generate.intent import DialogueIntent, IntentTag
 from generate.proposition import Proposition
+from teaching.source import ProposalSource
 from teaching.store import PackMutationProposal
 
 
@@ -122,6 +123,9 @@ def test_pack_plus_teaching() -> None:
         subject="x",
         correction_text="x is z",
         prior_surface="x is y",
+        source=ProposalSource(
+            kind="operator", source_id="", emitted_at_revision="test"
+        ),
     )
     result = _make_result(
         intent_tag=IntentTag.CORRECTION,

tests/test_realizer_guard_holdout.py

@@ -77,21 +77,25 @@ def test_each_confirmation_prompt_now_articulates(
 # ---------- byte-identity invariant on currently-passing cases ----------
 
 
+# Surfaces re-pinned after the gloss-aware composer landed; the prior
+# strings (e.g. "Light is a source of revelation that makes things knowable.")
+# were superseded by gloss-driven phrasings ("Light is a visible medium
+# that reveals truth.") that are visibly more grounded. The byte-identity
+# guard role is preserved by pinning the current outputs going forward.
 _CURRENTLY_PASSING_PROMPTS: tuple[tuple[str, str], ...] = (
     (
         "What is light?",
-        "Light is a source of revelation that makes things knowable. "
+        "Light is a visible medium that reveals truth. "
         "pack-grounded (en_core_cognition_v1).",
     ),
     (
         "Define knowledge.",
-        "Knowledge is justified understanding grounded in evidence "
+        "Knowledge is what a person knows from truth and evidence. "
-        "and recall. pack-grounded (en_core_cognition_v1).",
+        "pack-grounded (en_core_cognition_v1).",
     ),
     (
         "What is truth?",
-        "Truth is a claim or state grounded by evidence and coherent "
+        "Truth is what is true. pack-grounded (en_core_cognition_v1).",
-        "judgment. pack-grounded (en_core_cognition_v1).",
     ),
 )
 

tests/test_register_runtime_threading.py

@@ -45,6 +45,9 @@ REGISTER_AWARE_COMPOSERS: frozenset[str] = frozenset(
         # called from chat/runtime.py directly, so the
         # runtime-threading lint passes trivially.
         "build_pack_surface_candidate",
+        "gloss_aware_cause_surface",
+        "pack_grounded_unknown_surface",
+        "teaching_grounded_surface_transitive",
     }
 )
 

tests/test_register_substantive_consumption.py

@@ -59,11 +59,11 @@ def _r(overrides: Mapping[str, object]) -> _FakeRegister:
 
 
 _DEF_CANONICAL = (
-    "Light is a source of revelation that makes things knowable. "
+    "Light is a visible medium that reveals truth. "
     "pack-grounded (en_core_cognition_v1)."
 )
 _DEF_CANONICAL_LENS = (
-    "Light is a source of revelation that makes things knowable. "
+    "Light is a visible medium that reveals truth. "
     "pack-grounded (en_core_cognition_v1) [lens(grc_logos_v1):systematic]."
 )
 _CMP_CANONICAL = (
@@ -115,7 +115,7 @@ def test_drop_provenance_strips_trailing_gloss_clause():
         _DEF_CANONICAL, _r({"drop_provenance_tag": True}),
     )
     assert "pack-grounded" not in out
-    assert out.endswith("knowable.")
+    assert out.endswith("reveals truth.")
     assert "..," not in out and ".." not in out  # no double-period bug
 
 
@@ -288,10 +288,10 @@ def test_terse_full_combo_def_form():
             "drop_articles": True,
         }),
     )
-    # compress: "Light is a source ... knowable." -> "Light: source ... knowable."
+    # compress: "Light is a visible medium ... truth." -> "Light: visible medium ... truth."
-    # drop_articles: removes leftover "a/the" articles (none in this gloss).
+    # drop_articles: removes leftover "a/the" articles.
     # drop_provenance_tag: trailing pack-grounded clause removed.
-    assert out == "Light: source of revelation that makes things knowable."
+    assert out == "Light: visible medium that reveals truth."
 
 
 def test_terse_full_combo_with_lens():
@@ -409,7 +409,7 @@ def test_e2e_neutral_unchanged_by_r6(neutral_def_surface: str):
     """default_neutral_v1 has no R6 knobs → surface must be identical
     to the pre-R6 byte-for-byte expected gloss."""
     expected = (
-        "Light is a source of revelation that makes things knowable. "
+        "Light is a visible medium that reveals truth. "
         "pack-grounded (en_core_cognition_v1)."
     )
     assert neutral_def_surface == expected

tests/test_transitive_surface.py

@@ -242,6 +242,7 @@ def test_cognition_lane_metrics_unchanged_with_transitive_flag() -> None:
     expected_surface_contains assertion that passed flag-OFF must still
     pass flag-ON.  If a future change ever drops tokens in transitive
     mode, this test fails as the deliberate regression it is."""
+    import os
     from evals.framework import get_lane, run_lane
 
     lane = get_lane("cognition")
@@ -256,7 +257,15 @@ def test_cognition_lane_metrics_unchanged_with_transitive_flag() -> None:
         transitive_surface=True,
         transitive_max_depth=2,
     )
-    for split in ("public", "holdout"):
+    # holdout requires CORE_HOLDOUT_KEY or a sibling cases_plaintext.jsonl;
+    # skip it on contributor machines without the sealed key.
+    sealed = lane.holdout_cases_path_sealed()
+    holdout_available = (
+        os.environ.get("CORE_HOLDOUT_KEY") is not None
+        or (sealed.parent / "cases_plaintext.jsonl").exists()
+    )
+    splits = ("public", "holdout") if holdout_available else ("public",)
+    for split in splits:
         off = run_lane(lane, version="v1", split=split,
                        config=RuntimeConfig()).metrics
         on = run_lane(lane, version="v1", split=split,